© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8877
    Prev
    Next
    INDEX
    Explanations

    SDK

    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
    Negative Logits
     Powers
    -0.55
    YesNo
    -0.54
     Objekt
    -0.54
    osoba
    -0.52
     statysty
    -0.50
    znamu
    -0.50
    heid
    -0.49
     spalle
    -0.49
    abase
    -0.49
     Virol
    -0.49
    POSITIVE LOGITS
    клопе
    0.60
    addCriterion
    0.56
    InjectAttribute
    0.54
    simile
    0.54
    createComponent
    0.53
    contentLoaded
    0.52
    영어
    0.52
    elemField
    0.51
    migrationBuilder
    0.50
     fubject
    0.50
    Activations Density 0.040%

    No Known Activations