© 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. 91089
    Prev
    Next
    INDEX
    Explanations

    (

    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
    Cordialement
    -0.52
     ویکی‌پدیای
    -0.52
     Vikipedi
    -0.51
     easier
    -0.50
     beginnetje
    -0.49
     Exacts
    -0.48
     Steffen
    -0.48
     Dekker
    -0.48
    archiviato
    -0.48
     Reverso
    -0.47
    POSITIVE LOGITS
    char
    0.56
    int
    0.54
     (?,
    0.52
    unsigned
    0.48
    uint
    0.47
     ("
    0.47
    !(
    0.47
    CAPTION
    0.47
     (
    0.47
    float
    0.45
    Activations Density 0.067%

    No Known Activations