© 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. 1-CLT-HP
    7. 9966
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    tagHelperRunner
    -0.85
    antum
    -0.74
     conveys
    -0.60
    "]]
    -0.55
    __*/
    -0.55
    vatar
    -0.53
    Erreferentziak
    -0.52
    mately
    -0.50
    CppCodeGen
    -0.50
    _));
    -0.50
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.56
     yoghurt
    0.55
    RegressionTest
    0.54
    WebVitals
    0.54
    MigrationBuilder
    0.54
    Feign
    0.52
    verwijspagina
    0.52
    featureID
    0.50
    UVWXYZ
    0.50
    PRWEB
    0.49
    Activations Density 0.064%

    No Known Activations