© 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. 39950
    Prev
    Next
    INDEX
    Explanations

    I

    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
    
    -0.56
    Obrázky
    -0.49
    ThroughAttribute
    -0.48
    AndEndTag
    -0.48
    +#+#
    -0.47
    CloseOperation
    -0.46
    تقاوى
    -0.46
    ValueStyle
    -0.45
    jooq
    -0.43
    picasso
    -0.42
    POSITIVE LOGITS
     myſelf
    0.92
     purpoſe
    0.82
     defire
    0.79
     congratulate
    0.77
     ſhall
    0.73
     himſelf
    0.72
     congratulated
    0.71
     itſelf
    0.71
     ſtand
    0.69
     planas
    0.68
    Activations Density 0.025%

    No Known Activations