© 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. 1-CLT-HP
    7. 9000
    Prev
    Next
    INDEX
    Explanations

    returning

    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
    سطس
    -0.51
    onFocus
    -0.48
     posteriorly
    -0.46
     experimentally
    -0.45
    FromJson
    -0.45
    يتها
    -0.45
     ympä
    -0.45
     kuten
    -0.44
     from
    -0.44
    前から
    -0.44
    POSITIVE LOGITS
    BeginContext
    0.81
    ьаж
    0.63
     Meals
    0.61
     LUMP
    0.60
    ERTS
    0.57
    rrggbb
    0.57
     lebe
    0.56
    GEBURTSDATUM
    0.56
    ércoles
    0.55
    zzleHttp
    0.55
    Activations Density 0.005%

    No Known Activations