© 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. 97506
    Prev
    Next
    INDEX
    Explanations

    v

    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
     V
    -0.92
     v
    -0.91
     surla
    -0.90
    styleType
    -0.82
     autorytatywna
    -0.81
    V
    -0.79
    帖最后由
    -0.73
    存于互联网档案馆
    -0.71
     للمعارف
    -0.69
    :+:
    -0.69
    POSITIVE LOGITS
    con
    0.54
    Er
    0.44
    nc
    0.44
    8
    0.44
    dc
    0.44
    cr
    0.44
    ca
    0.43
    tt
    0.42
    fan
    0.42
    st
    0.41
    Activations Density 0.170%

    No Known Activations