© 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. 20-CLT-HP
    7. 71602
    Prev
    Next
    INDEX
    Explanations

    X-ray crystallography

    np_max-act-logits · 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
     للمعارف
    -0.57
    escens
    -0.53
     spesa
    -0.51
    vá
    -0.50
    ValueStyle
    -0.50
     rédaction
    -0.50
    MigrationBuilder
    -0.50
     שוליים
    -0.49
    execSQL
    -0.49
    closePath
    -0.49
    POSITIVE LOGITS
     opérés
    0.56
     onOptions
    0.50
     onlyOwner
    0.47
    ısında
    0.46
     GON
    0.46
     wors
    0.45
     unsecured
    0.45
    
    0.45
     NUKAT
    0.44
     ErrIntOverflow
    0.44
    Activations Density 0.001%

    No Known Activations