© 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

    print function calls (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
    code
    -0.06
    de
    -0.05
    roup
    -0.03
    l
    -0.03
    sp
    -0.03
    ample
    -0.02
    ay
    -0.02
     or
    -0.02
    les
    -0.01
    ree
    -0.01
    Positive Logits
     ]↵
    0.10
     }↵
    0.10
     },↵
    0.09
    ]))↵
    0.05
    ]):↵
    0.05
    ])
    0.05
     Returns
    0.04
    ):
    0.04
    ),
    0.04
     Ex
    0.04
    Activations Density 84.750%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    mean, quantity, manufacturer, radians

    python-code · gemini-2.5-flash-lite

    end of method call (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
    ateg
    -0.10
                           
    -0.08
    ype
    -0.07
    lat
    -0.07
    arent
    -0.06
    ree
    -0.06
    ry
    -0.06
    ighbor
    -0.06
    isit
    -0.06
    ample
    -0.05
    Positive Logits
    xF
    0.07
    ross
    0.06
    reshold
    0.05
    ·
    0.05
    ange
    0.04
    pected
    0.04
    ents
    0.04
    (con
    0.04
    en
    0.04
     with
    0.04
    Activations Density 100.000%

    No Known Activations