© 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. 45176
    Prev
    Next
    INDEX
    Explanations

    advisor/system

    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
     System
    -1.05
    System
    -1.04
     adviser
    -0.79
     advised
    -0.73
    advisor
    -0.73
    icksburg
    -0.71
    Advisor
    -0.70
    advised
    -0.69
     ADVIS
    -0.68
     Adviser
    -0.67
    POSITIVE LOGITS
     Monfieur
    0.78
     myſelf
    0.76
     Theſe
    0.75
    ſelf
    0.72
     poffe
    0.72
     himſelf
    0.69
     pleaſure
    0.69
     houſe
    0.68
     itſelf
    0.66
     ſeveral
    0.66
    Activations Density 0.110%

    No Known Activations