© 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
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95619
    Prev
    Next
    INDEX
    Explanations

    scientific/technical descriptions

    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
    Negative Logits
     للاسماء
    -0.79
     bag
    -0.77
    StoreMessageInfo
    -0.77
    المكان
    -0.73
     saites
    -0.71
     NSCoder
    -0.70
    GEBURTSDATUM
    -0.69
     оригіналу
    -0.68
     Meksiku
    -0.68
    DECREF
    -0.67
    POSITIVE LOGITS
    s
    0.66
    st
    0.55
    mo
    0.55
    tt
    0.55
    da
    0.53
    ting
    0.53
    do
    0.52
    so
    0.51
    ungen
    0.51
    lla
    0.50
    Activations Density 0.541%

    No Known Activations