© 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. 95470
    Prev
    Next
    INDEX
    Explanations

    larynx

    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
    ed
    -0.66
    i
    -0.62
    tout
    -0.57
     grounded
    -0.54
     glued
    -0.54
    e
    -0.50
    eu
    -0.50
    eg
    -0.49
    ii
    -0.49
    stick
    -0.49
    POSITIVE LOGITS
    ագրություններ
    0.74
     Réponses
    0.63
     للاسماء
    0.60
     ویکی‌پدیا
    0.59
     الحره
    0.58
     Мексичка
    0.58
     Audiodateien
    0.56
     ostavi
    0.55
    CrossRef
    0.54
     Winaray
    0.54
    Activations Density 0.042%

    No Known Activations