© 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. 20-CLT-HP
    7. 75108
    Prev
    Next
    INDEX
    Explanations

    Weapons and combat

    np_max-act-logits · 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
    providedIn
    -0.80
    ViewFeatures
    -0.67
     muualla
    -0.65
    bollah
    -0.61
    KommentareTeilen
    -0.57
    ScopeManager
    -0.57
    出版年
    -0.57
    XmlAccessType
    -0.54
     Monet
    -0.54
    contentLoaded
    -0.54
    POSITIVE LOGITS
     jammed
    0.68
     fires
    0.61
     jams
    0.58
    Manbalar
    0.57
     cycle
    0.57
     jam
    0.57
     Jam
    0.56
    cycle
    0.54
     cycles
    0.53
     Cycle
    0.53
    Activations Density 0.000%

    No Known Activations