© 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. 91095
    Prev
    Next
    INDEX
    Explanations

    Officer

    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
     conclude
    -0.83
     concluding
    -0.72
     conclusions
    -0.71
     مرئيه
    -0.69
     conclud
    -0.66
     Officer
    -0.65
     Conclusion
    -0.63
     Conclusions
    -0.62
     conclu
    -0.60
     closing
    -0.60
    POSITIVE LOGITS
     Efq
    0.90
     RSSSF
    0.78
     Majefty
    0.75
     myſelf
    0.74
     Monfieur
    0.72
     moschino
    0.68
     ſeveral
    0.68
     Diſ
    0.66
     Houſe
    0.66
     fhew
    0.66
    Activations Density 0.047%

    No Known Activations