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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93455
    Prev
    Next
    INDEX
    Explanations

    sonic

    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
     ―――――
    -0.87
    oas
    -0.86
     ་་
    -0.86
    ImageContext
    -0.82
     Vang
    -0.80
    )");
    -0.79
    )";
    -0.77
    endregion
    -0.77
     itſelf
    -0.76
    eleste
    -0.75
    POSITIVE LOGITS
    by
    0.43
    ak
    0.43
    Selen
    0.41
    enter
    0.39
    aw
    0.38
    ons
    0.37
    unt
    0.37
    хи
    0.37
    ow
    0.36
    if
    0.36
    Activations Density 0.145%

    No Known Activations