© 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. 38774
    Prev
    Next
    INDEX
    Explanations

    bra

    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
     bra
    -0.87
     gynhyrchwyd
    -0.76
     Winn
    -0.73
    Bra
    -0.72
    bra
    -0.68
     Италијани
    -0.67
     censiti
    -0.65
     الاطلاع
    -0.65
    AntiForgeryToken
    -0.65
    SuccessListener
    -0.64
    POSITIVE LOGITS
    ed
    0.50
    getMenuInflater
    0.42
    e
    0.42
    undai
    0.39
    cum
    0.39
    ised
    0.38
     ngh
    0.38
    KeySpec
    0.36
    es
    0.35
    乓
    0.35
    Activations Density 0.054%

    No Known Activations