© 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. 5-CLT-HP
    7. 6020
    Prev
    Next
    INDEX
    Explanations

    Chem

    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
     HasFactory
    -0.75
     autorytatywna
    -0.73
     estimés
    -0.68
     оригіналу
    -0.63
    -------------</
    -0.61
     CreateTagHelper
    -0.60
     للمعارف
    -0.58
    بوابة
    -0.57
    GEBURTSDATUM
    -0.56
    ArgsConstructor
    -0.55
    POSITIVE LOGITS
     ZU
    0.46
    SerializedSize
    0.44
     Administrativna
    0.43
    +#+#
    0.43
    Sint
    0.43
    urence
    0.42
    tabli
    0.42
    Saya
    0.41
     Chri
    0.41
    stwo
    0.41
    Activations Density 0.003%

    No Known Activations