© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 318
    Prev
    Next
    INDEX
    Explanations

    key statistics and findings related to data prevalence and comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Задачи
    -0.45
    OfWork
    -0.45
    InlineData
    -0.44
    
    -0.44
    ละเอียด
    -0.43
     CGSize
    -0.43
    Koordinaten
    -0.42
    tableData
    -0.42
     almofada
    -0.41
     frumo
    -0.41
    POSITIVE LOGITS
     best
    0.96
     strongest
    0.91
     highest
    0.90
     BEST
    0.90
     largest
    0.88
    best
    0.87
     greatest
    0.87
     biggest
    0.87
     fastest
    0.86
     safest
    0.86
    Activations Density 1.806%

    No Known Activations