© 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. 3-RES-MATRYOSHKA-DC
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    the word "season" when referring to sports

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    الدراسه
    -0.63
    IBOutlet
    -0.58
    ankara
    -0.56
    submitted
    -0.55
     fact
    -0.54
     banca
    -0.52
     ar
    -0.51
     continuant
    -0.51
    GetKeyDown
    -0.50
    hite
    -0.50
    POSITIVE LOGITS
     season
    2.75
     seasons
    2.53
    season
    2.48
     Season
    2.44
    Season
    2.44
     SEASON
    2.41
    seasons
    2.17
    SEASON
    2.17
     Seasons
    2.05
    Seasons
    1.96
    Activations Density 0.030%

    No Known Activations