© 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

    closing parenthesis or bracket after code block (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
    an
    -0.08
     colle
    -0.07
     main
    -0.05
    ome
    -0.05
    main
    -0.05
    ain
    -0.04
    ax
    -0.04
    __':↵
    -0.04
     as
    -0.03
     at
    -0.03
    Positive Logits
    ry
    0.09
    con
    0.06
    iti
    0.06
    ary
    0.05
    gment
    0.04
                   
    0.04
    gle
    0.04
                       
    0.04
    utation
    0.04
               
    0.03
    Activations Density 99.433%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    calling sorted() function

    python-code · gemini-2.5-flash-lite

    assignment to variable `e` (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
    Ĥ
    -0.03
    Ĺ
    -0.02
    che
    -0.02
    put
    -0.02
    ı
    -0.01
    loc
    -0.01
    ok
    -0.01
    ci
    -0.01
    ak
    -0.01
    ings
    -0.01
    Positive Logits
    reshold
    0.05
    ange
    0.04
    ents
    0.03
    ency
    0.03
    ood
    0.03
    ain
    0.03
    en
    0.03
    ent
    0.03
    rib
    0.03
    ateg
    0.03
    Activations Density 100.000%

    No Known Activations