© 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. 94215
    Prev
    Next
    INDEX
    Explanations

    antimicrobial

    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
    rostis
    -0.82
    rrggbb
    -0.78
    parsedMessage
    -0.68
    ItemBackground
    -0.67
     cuarentena
    -0.64
    olingo
    -0.63
    rouvez
    -0.62
    wegg
    -0.62
     actionMode
    -0.61
    aarrggbb
    -0.60
    POSITIVE LOGITS
    ality
    0.64
    ی
    0.61
    ness
    0.59
    fällen
    0.59
     useParams
    0.57
     års
    0.56
    ي
    0.56
    الإنجليزية
    0.56
     sensitivity
    0.55
    ensitive
    0.55
    Activations Density 0.077%

    No Known Activations