© 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. 42285
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     mẫu
    -0.45
    مكن
    -0.45
     anything
    -0.44
     sites
    -0.44
    gorod
    -0.43
     Schrift
    -0.43
    вгения
    -0.42
    itan
    -0.42
    DIRS
    -0.41
     its
    -0.41
    POSITIVE LOGITS
    mybatisplus
    0.96
    yntaxException
    0.84
    abestanden
    0.77
     للمعارف
    0.75
    hysema
    0.74
     تضيفلها
    0.73
     Савезне
    0.71
     autorytatywna
    0.67
     arşivlendi
    0.65
    Obrázky
    0.65
    Activations Density 0.048%

    No Known Activations