© 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
    No Explanations Found
    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
    yp
    -0.09
     re
    -0.09
     we
    -0.06
     exp
    -0.06
     in
    -0.06
    f
    -0.06
     tra
    -0.04
     per
    -0.04
     en
    -0.04
    =
    -0.04
    Positive Logits
    cess
    0.08
    term
    0.05
     dp
    0.05
     process
    0.05
    zero
    0.05
    pro
    0.04
    (N
    0.04
    over
    0.04
     char
    0.04
    dint
    0.04
    Activations Density 27.954%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    __ and ____ (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
    um
    -0.12
    opulation
    -0.08
                 
    -0.08
                
    -0.08
     student
    -0.08
                  
    -0.08
                                    
    -0.08
                    
    -0.08
     population
    -0.07
    _population
    -0.07
    Positive Logits
    h
    0.08
     defaultdict
    0.08
    igh
    0.06
     h
    0.06
    house
    0.06
    _h
    0.05
    hor
    0.05
     else
    0.04
    <extra_output_id:2047>
    0.04
     name
    0.04
    Activations Density 97.684%

    No Known Activations