© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91039
    Prev
    Next
    INDEX
    Explanations

    Washington

    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
     Washington
    -0.59
    🇶
    -0.50
     regional
    -0.50
    +#+
    -0.48
     {;
    -0.47
    :+:
    -0.47
    pédie
    -0.46
     exportación
    -0.45
    force
    -0.45
    hyperref
    -0.44
    POSITIVE LOGITS
     Diſ
    0.93
     Houſe
    0.85
     ―――――
    0.82
     Monfieur
    0.76
     myſelf
    0.75
     itſelf
    0.75
     ſche
    0.74
     Majefty
    0.70
     poffe
    0.69
     Jefus
    0.68
    Activations Density 0.021%

    No Known Activations