© 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. 4-CLT-HP
    7. 3283
    Prev
    Next
    INDEX
    Explanations

    code, logs, random text

    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
    -0.91
     esternos
    -0.84
    ConstraintMaker
    -0.83
    OGND
    -0.78
     للاسماء
    -0.75
    出版年
    -0.74
     ddelweddau
    -0.73
     ProtoMessage
    -0.72
     للمعارف
    -0.70
    ArgsConstructor
    -0.68
    POSITIVE LOGITS
    EXACT
    0.41
    assertEqual
    0.39
    olska
    0.37
     únicas
    0.36
     Stelle
    0.36
     strictest
    0.35
    Scott
    0.35
    SS
    0.35
     arrangements
    0.35
     toepassing
    0.35
    Activations Density 0.001%

    No Known Activations