© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute names starting with 'di' or 'si'

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ta
    -0.04
    ati
    -0.03
    L
    -0.02
    uccess
    -0.02
    c
    -0.02
     L
    -0.02
    ±
    -0.02
    U
    -0.02
    tive
    -0.02
     U
    -0.01
    Positive Logits
     height
    0.05
    _height
    0.05
    men
    0.04
    idth
    0.04
     width
    0.04
    m
    0.04
    (m
    0.04
     m
    0.03
     right
    0.03
    right
    0.03
    Activations Density 39.564%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `self.` attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    except clause

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    lat
    -0.05
    itude
    -0.05
     lat
    -0.04
    ge
    -0.03
     },↵
    -0.03
    .random
    -0.02
                       
    -0.02
                           
    -0.02
                   
    -0.02
                    
    -0.02
    Positive Logits
     while
    0.05
     continue
    0.05
     break
    0.05
     raise
    0.04
    .split
    0.04
     elif
    0.04
    print
    0.04
     print
    0.04
     return
    0.04
     else
    0.04
    Activations Density 90.685%

    No Known Activations