© 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. 4767
    Prev
    Next
    INDEX
    Explanations

    [

    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
     légitime
    -0.57
    amaño
    -0.57
     constaté
    -0.57
     popoli
    -0.57
    mässig
    -0.56
     lunak
    -0.55
    avoit
    -0.54
     alvor
    -0.54
     spørs
    -0.54
     or
    -0.54
    POSITIVE LOGITS
    RegressionTest
    0.63
     “
    0.56
    XmlEnum
    0.52
     Wiktionnaire
    0.52
     “[
    0.52
    liferay
    0.49
    قات
    0.49
    octanol
    0.49
     "[
    0.47
    ורה
    0.47
    Activations Density 0.000%

    No Known Activations