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. 1-CLT-HP
    4. 45391
    Prev
    Next
    INDEX
    Explanations

    wine

    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
    LookAnd
    -0.64
     balanceOf
    -0.60
    CopyWith
    -0.60
    MLLoader
    -0.59
     Supervisory
    -0.56
     muualla
    -0.56
     Sulfate
    -0.55
     Erosion
    -0.55
    isContained
    -0.55
     Jurisdiction
    -0.55
    POSITIVE LOGITS
    dark
    0.58
    DockStyle
    0.58
    Dark
    0.55
    vat
    0.52
     Dark
    0.52
     dark
    0.51
     standing
    0.50
    press
    0.50
    punch
    0.49
    glass
    0.47
    Activations Density 0.006%

    No Known Activations