© 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

    assignment to variable `a`

    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
     ]↵
    -0.09
     },↵
    -0.09
    )],↵
    -0.06
     }↵
    -0.06
    ))<|
    -0.06
    ])↵↵
    -0.05
    ]),
    -0.05
    )]↵↵
    -0.05
    ]))↵
    -0.05
    ]):↵
    -0.05
    Positive Logits
    h
    0.06
    igh
    0.05
    .split
    0.05
    from
    0.04
     h
    0.04
    house
    0.04
    split
    0.04
    .read
    0.04
    .strip
    0.04
    ()
    0.04
    Activations Density 49.421%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    self followed by colon or comma

    python-code · gemini-2.5-flash-lite

    token after comma (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
    timal
    -0.06
    losest
    -0.06
     optimal
    -0.05
     best
    -0.05
     closest
    -0.05
    gest
    -0.04
    arest
    -0.04
    hortest
    -0.04
    verage
    -0.04
     shortest
    -0.04
    Positive Logits
     dfs
    0.06
     between
    0.05
    loat
    0.03
    isit
    0.03
    _ch
    0.02
    1
    0.02
    ch
    0.02
    .ch
    0.02
     ch
    0.02
     char
    0.02
    Activations Density 94.104%

    No Known Activations