© 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. 1-CLT-HP
    7. 12967
    Prev
    Next
    INDEX
    Explanations

    Acid

    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
    principalTable
    -0.83
     فريبيس
    -0.81
    Acid
    -0.70
     Acid
    -0.63
     aDecoder
    -0.63
    irage
    -0.59
    pherals
    -0.58
    #
    -0.57
    RSpec
    -0.57
    AutoresizingMask
    -0.56
    POSITIVE LOGITS
    ic
    1.14
    IC
    0.75
    SharedDtor
    0.60
     Fall
    0.57
    ry
    0.55
    ian
    0.54
    ică
    0.50
    ig
    0.49
    pushFollow
    0.49
    ik
    0.47
    Activations Density 0.077%

    No Known Activations