© 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. 5-CLT-HP
    7. 5770
    Prev
    Next
    INDEX
    Explanations

    site

    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
    Autoritní
    -1.10
    Personensuche
    -0.93
    aarrggbb
    -0.91
     ISNI
    -0.85
    expandindo
    -0.84
    lapsingToolbar
    -0.73
    ^(@)
    -0.71
    RenderAtEndOf
    -0.70
     Paglinawan
    -0.69
     الرياضيه
    -0.68
    POSITIVE LOGITS
    maxcdn
    0.54
     of
    0.47
     simply
    0.45
     useRef
    0.43
     fapt
    0.43
    EndContext
    0.43
     clear
    0.43
     merely
    0.42
    .
    0.42
     lot
    0.41
    Activations Density 0.003%

    No Known Activations