© 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. 5-CLT-HP
    7. 95263
    Prev
    Next
    INDEX
    Explanations

    authorities

    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
    Hentet
    -0.68
    出版年
    -0.67
    ]")]
    -0.64
     binds
    -0.63
    헌
    -0.62
    richTextPanel
    -0.61
     meurt
    -0.60
    AutoScaleMode
    -0.60
     entré
    -0.59
     disponibilités
    -0.58
    POSITIVE LOGITS
     have
    0.96
     are
    0.95
     were
    0.68
     intend
    0.67
     plan
    0.66
     hope
    0.66
     haven
    0.63
     expect
    0.62
     believe
    0.62
     seem
    0.61
    Activations Density 0.001%

    No Known Activations