© 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. 91004
    Prev
    Next
    INDEX
    Explanations

    ated

    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
    êmio
    -0.48
     decorator
    -0.47
     ویکی‌پدیا
    -0.46
    UnsafeEnabled
    -0.46
     russe
    -0.45
     utom
    -0.44
    phie
    -0.44
     OUTSIDE
    -0.44
     dij
    -0.43
     anarch
    -0.43
    POSITIVE LOGITS
    <bos>
    0.64
    endpush
    0.56
    Amicalement
    0.56
    SerializedName
    0.55
    Šaltiniai
    0.55
    发表于
    0.54
    Билгалдахарш
    0.52
     Vary
    0.52
    jalá
    0.51
     Assignee
    0.51
    Activations Density 0.137%

    No Known Activations