© 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. 94302
    Prev
    Next
    INDEX
    Explanations

    promoted

    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
     promoted
    -2.27
     promote
    -2.22
     promotion
    -2.20
     promoting
    -2.06
     Promotion
    -2.03
     Promote
    -1.99
    promote
    -1.98
    promotion
    -1.91
    Promote
    -1.89
    promoted
    -1.89
    POSITIVE LOGITS
    GEBURTSDATUM
    0.66
     fevere
    0.54
    hetically
    0.54
    CLUYE
    0.54
     noexcept
    0.51
    culously
    0.51
    PTT
    0.50
    AntiForgeryToken
    0.50
    TESTS
    0.49
     Palladium
    0.49
    Activations Density 0.247%

    No Known Activations