© 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. 94719
    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
     оригіналу
    -0.60
    }();
    -0.60
     للمعارف
    -0.57
     Grecs
    -0.54
    homonymie
    -0.54
     jouets
    -0.53
     Juifs
    -0.53
    المشاركات
    -0.53
     investissements
    -0.53
     Bourgoin
    -0.52
    POSITIVE LOGITS
    .
    1.11
    0
    0.95
    ,
    0.94
     to
    0.87
    %
    0.84
    -
    0.82
     million
    0.79
     or
    0.71
     out
    0.71
    /
    0.71
    Activations Density 0.001%

    No Known Activations