© 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. 28
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and performance highlights

    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
    Not in Any Lists

    No Comments

    Negative Logits
     familles
    -0.59
     scienza
    -0.58
     systèmes
    -0.56
     nonUne
    -0.56
     naturen
    -0.55
     technologies
    -0.54
     systems
    -0.54
     sociétés
    -0.52
     computadoras
    -0.52
     exemples
    -0.52
    POSITIVE LOGITS
     unbeaten
    0.71
     playoff
    0.64
     الرياضيه
    0.63
     undefeated
    0.63
     played
    0.62
     rival
    0.60
     sidelined
    0.59
     twice
    0.58
     playoffs
    0.56
     coached
    0.54
    Activations Density 3.227%

    No Known Activations