© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1107
    Prev
    Next
    INDEX
    Explanations

    times

    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
     autorytatywna
    -0.96
     times
    -0.77
     Times
    -0.65
     TIMES
    -0.65
    LookAnd
    -0.63
     ProtoMessage
    -0.62
     referenties
    -0.58
    FontOfSize
    -0.57
     bezeichneter
    -0.57
     perpetuity
    -0.57
    POSITIVE LOGITS
    hips
    0.88
     seules
    0.56
    teps
    0.56
    cales
    0.56
    lots
    0.56
     liés
    0.54
    omeness
    0.54
     ouverts
    0.54
     liée
    0.54
     forze
    0.52
    Activations Density 0.058%

    No Known Activations