© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 15529
    Prev
    Next
    INDEX
    Explanations

    technical/legal documents

    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
     AspNetCore
    -0.78
    pherson
    -0.73
     mergeFrom
    -0.68
    帖最后由
    -0.67
    ValueStyle
    -0.67
     oprot
    -0.67
    rungsseite
    -0.65
    Pherson
    -0.65
     שוליים
    -0.65
     تانيه
    -0.64
    POSITIVE LOGITS
     وتسجيلات
    0.52
     olvides
    0.48
    seamnă
    0.43
     florales
    0.42
     rayures
    0.42
     detaljer
    0.41
     nuages
    0.40
    medel
    0.40
    antaranya
    0.40
     exprimer
    0.40
    Activations Density 0.010%

    No Known Activations