© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    scientists

    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
    Personensuche
    -0.89
    ThroughAttribute
    -0.88
     שוליים
    -0.79
    AccessorTable
    -0.77
     scientists
    -0.74
     }}"></
    -0.73
    +#+#
    -0.72
    StoreMessageInfo
    -0.72
     ويكيميديا
    -0.71
    StructEnd
    -0.70
    POSITIVE LOGITS
    <bos>
    0.49
    zler
    0.48
    годня
    0.45
    letal
    0.44
     oportun
    0.43
    yní
    0.42
    نت
    0.40
    postmedia
    0.40
     bav
    0.40
    assertIs
    0.39
    Activations Density 0.108%

    No Known Activations