© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13546
    Prev
    Next
    INDEX
    Explanations

    shock

    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
     shock
    -1.19
    Shock
    -1.06
    shock
    -1.05
     Shock
    -1.04
     SHOCK
    -0.83
     shocks
    -0.83
     shocked
    -0.69
    shocked
    -0.68
    hock
    -0.68
    ショック
    -0.56
    POSITIVE LOGITS
    GEBURTSDATUM
    0.76
    tagHelperRunner
    0.73
     مشين
    0.71
    ագրություններ
    0.69
     Normdatei
    0.69
    UseVisualStyle
    0.65
     ―――――
    0.65
    parsedMessage
    0.64
     blanches
    0.62
     EconPapers
    0.62
    Activations Density 0.007%

    No Known Activations