© 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. 71347
    Prev
    Next
    INDEX
    Explanations

    Land/Lend

    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
    Negative Logits
    protoc
    -0.74
    
    -0.66
    +#+#
    -0.66
     iprot
    -0.61
    rader
    -0.61
    migrationBuilder
    -0.58
    iprot
    -0.54
    iastical
    -0.54
     Efq
    -0.54
    EndInit
    -0.53
    POSITIVE LOGITS
     المعيارى
    0.78
    enumi
    0.54
    Chham
    0.52
    SequentialGroup
    0.52
    StateManager
    0.43
    wer
    0.42
    참고
    0.42
    nore
    0.41
    Américaine
    0.40
     Card
    0.40
    Activations Density 0.001%

    No Known Activations