© 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

    re.compile or re.finditer

    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
    ±
    -0.05
    _grid
    -0.03
    07
    -0.03
    bab
    -0.02
                       
    -0.02
    ti
    -0.02
    @
    -0.01
    oc
    -0.01
     grid
    -0.01
                   
    -0.01
    Positive Logits
    e
    0.09
    es
    0.06
    m
    0.06
    me
    0.06
    ed
    0.04
    mo
    0.04
    M
    0.04
    mm
    0.04
    em
    0.03
    mory
    0.03
    Activations Density 8.800%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment statement

    python-code · gemini-2.5-flash-lite

    `for` loops and `int()` casting (negative activations)

    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
    .name
    -0.04
    .id
    -0.04
    _idx
    -0.03
    dex
    -0.03
    _index
    -0.02
    uel
    -0.02
     op
    -0.02
    _cost
    -0.02
    value
    -0.02
    <|
    -0.02
    Positive Logits
    valid
    0.02
    sible
    0.02
    ab
    0.02
     shortest
    0.01
     sele
    0.01
    (n
    0.01
     it
    0.01
    hi
    0.01
    py
    0.01
    }
    0.00
    Activations Density 85.715%

    No Known Activations