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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42846
    Prev
    Next
    INDEX
    Explanations

    action

    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
     action
    -1.54
     Action
    -1.39
    Action
    -1.28
     actions
    -1.27
     ACTION
    -1.23
    action
    -1.17
     Actions
    -1.16
    ACTION
    -1.11
     acting
    -1.05
     acción
    -1.02
    POSITIVE LOGITS
    ValueStyle
    0.77
     الرياضيه
    0.75
    HideFlags
    0.69
     EconPapers
    0.68
     समीक्षाओं
    0.67
    principalColumn
    0.65
     насељу
    0.65
    KommentareTeilen
    0.63
    writeField
    0.60
     autorytatywna
    0.58
    Activations Density 0.873%

    No Known Activations