Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44571
    Prev
    Next
    INDEX
    Explanations

    professions

    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
     missing
    -0.88
     Efq
    -0.74
    principalTable
    -0.68
    Closer
    -0.68
    fillType
    -0.67
    missing
    -0.66
     Closer
    -0.66
    хьтан
    -0.65
    Халык
    -0.64
    ècie
    -0.63
    POSITIVE LOGITS
    ness
    0.58
    DllImport
    0.52
    TagMode
    0.50
    Rhestr
    0.46
    addGap
    0.43
    saf
    0.43
     الحره
    0.43
     cama
    0.43
     ness
    0.43
    NESS
    0.43
    Activations Density 0.221%

    No Known Activations