© 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. 4-CLT-HP
    7. 449
    Prev
    Next
    INDEX
    Explanations

    the

    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
    GraphicsUnit
    -0.57
    χρι
    -0.56
     Meksiku
    -0.55
    WriteTagHelper
    -0.53
     leksikon
    -0.50
    ThroughAttribute
    -0.50
     needful
    -0.49
    Hentet
    -0.49
    DoubleQuotes
    -0.47
    EDEFAULT
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.63
     endregion
    0.54
     growing
    0.52
     COVID
    0.52
    demment
    0.52
     Obrador
    0.52
     fall
    0.51
    */),
    0.51
     []).
    0.50
     on
    0.50
    Activations Density 0.004%

    No Known Activations