© 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. 95568
    Prev
    Next
    INDEX
    Explanations

    assay

    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
     wholesome
    -1.35
    wholesome
    -1.11
    olesome
    -0.82
    assay
    -0.68
     ویکی‌آمباردا
    -0.62
    ^(@)
    -0.61
     générations
    -0.61
    PRNewswire
    -0.56
     isempty
    -0.54
     heartwarming
    -0.54
    POSITIVE LOGITS
    ly
    0.91
    ится
    0.62
     nahilalakip
    0.57
    Билгалдахарш
    0.54
    able
    0.54
     دیکھیے
    0.53
    ever
    0.52
    ="@+
    0.52
    ulets
    0.52
    IsContent
    0.51
    Activations Density 1.684%

    No Known Activations