© 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. 42923
    Prev
    Next
    INDEX
    Explanations

    sword

    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
    adaptiveStyles
    -0.93
     armor
    -0.68
     sword
    -0.67
     movie
    -0.66
    Portale
    -0.66
     Roskov
    -0.65
    Autoritní
    -0.64
    PHeader
    -0.63
     chess
    -0.62
    Geplaatst
    -0.61
    POSITIVE LOGITS
    lite
    0.64
    worm
    0.59
    o
    0.55
    ing
    0.55
    y
    0.55
    sum
    0.54
    pin
    0.54
    store
    0.54
    krát
    0.53
    link
    0.52
    Activations Density 0.118%

    No Known Activations