© 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. 45041
    Prev
    Next
    INDEX
    Explanations

    politics

    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
     Republican
    -0.94
    Republican
    -0.85
     Conservative
    -0.83
     conservative
    -0.78
    Conservative
    -0.77
    conservative
    -0.76
     Democrat
    -0.70
     republican
    -0.68
    Democrat
    -0.65
     Cal
    -0.65
    POSITIVE LOGITS
     myſelf
    0.81
     itſelf
    0.76
     Majefty
    0.72
    ſelf
    0.71
     ſmall
    0.70
     Reſ
    0.70
     himſelf
    0.69
     ―――――
    0.69
     ſtate
    0.69
     ſeveral
    0.69
    Activations Density 1.819%

    No Known Activations