© 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. 1-CLT-HP
    7. 14561
    Prev
    Next
    INDEX
    Explanations

    rup

    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
    rupts
    -1.02
    rupted
    -0.79
    rup
    -0.75
    ruption
    -0.64
    RUPT
    -0.61
    RUP
    -0.57
    rupt
    -0.56
     disrupt
    -0.53
    rops
    -0.52
     effetto
    -0.50
    POSITIVE LOGITS
     the
    0.63
    fxml
    0.60
     ostavi
    0.55
    paccio
    0.55
    AnchorStyles
    0.54
     Schon
    0.54
    InputBorder
    0.54
    rotnie
    0.54
     mắn
    0.53
     typelib
    0.52
    Activations Density 0.037%

    No Known Activations