© 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. 5-CLT-HP
    7. 90957
    Prev
    Next
    INDEX
    Explanations

    Editor

    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
    ständige
    -0.49
    struzione
    -0.45
    providedIn
    -0.45
    AlterField
    -0.44
    ずみ
    -0.43
    UBL
    -0.43
    AndroidJUnit
    -0.43
     liderança
    -0.43
    Order
    -0.43
     Order
    -0.42
    POSITIVE LOGITS
    RegistryLite
    0.85
    ContentAsync
    0.67
     كومونز
    0.62
    rawDesc
    0.62
     للمعارف
    0.56
    الحياه
    0.55
    Enllaces
    0.54
    VersionUID
    0.54
    addCriterion
    0.54
     Fitzgerald
    0.53
    Activations Density 0.003%

    No Known Activations