© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90947
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreExecute
    -0.73
    prefixer
    -0.65
    );
    -0.63
    );
    -0.62
    ations
    -0.60
     Java
    -0.60
     autorytatywna
    -0.59
    WebpackPlugin
    -0.58
    |};
    -0.57
    WEBPACK
    -0.57
    POSITIVE LOGITS
     becauſe
    0.68
     whereas
    0.63
     ſmall
    0.62
     fossa
    0.61
    ToUse
    0.61
     auricular
    0.59
     Conſ
    0.57
    ۗ
    0.57
     unlike
    0.57
     Diſ
    0.56
    Activations Density 0.138%

    No Known Activations