© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42688
    Prev
    Next
    INDEX
    Explanations

    Senate

    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
    :✨
    -1.12
    RenderAtEndOf
    -1.09
     ainfi
    -0.95
    IntoConstraints
    -0.95
     Wikimedijinoj
    -0.93
     Antarctica
    -0.91
     Italy
    -0.90
    theless
    -0.89
    adaptiveStyles
    -0.89
    NameInMap
    -0.89
    POSITIVE LOGITS
    '
    0.81
    ’
    0.78
     and
    0.69
    ,
    0.67
     
    0.61
    -
    0.56
     is
    0.56
    .
    0.54
     in
    0.53
    /
    0.53
    Activations Density 0.092%

    No Known Activations