© 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. 38919
    Prev
    Next
    INDEX
    Explanations

    diverse

    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
     diverse
    -2.61
    diverse
    -2.48
     diversity
    -2.38
    Diverse
    -2.17
     Diverse
    -2.16
    diversity
    -2.11
     Diversity
    -1.88
    Diversity
    -1.87
     diversidad
    -1.81
     diversité
    -1.80
    POSITIVE LOGITS
    ly
    1.18
    LY
    0.69
    y
    0.67
    mybatisplus
    0.57
    mente
    0.54
     archa
    0.52
    lysis
    0.52
    ist
    0.51
    iy
    0.51
    IBOutlet
    0.51
    Activations Density 0.513%

    No Known Activations