© 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. 2-RES-MATRYOSHKA-DC
    7. 2631
    Prev
    Next
    INDEX
    Explanations

    references to lost or missing items, especially records of items that are no longer available

    oai_token-act-pair · gpt-4.1-nano
    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
     win
    -1.09
    win
    -0.93
     gain
    -0.91
    Win
    -0.84
     victory
    -0.83
     wins
    -0.83
     Win
    -0.81
     Gain
    -0.80
     WIN
    -0.79
     winnings
    -0.78
    POSITIVE LOGITS
     lost
    2.41
     Lost
    2.31
    lost
    2.27
    Lost
    2.27
     LOST
    2.14
    LOST
    1.98
     perdido
    1.59
     perdidos
    1.50
     verloren
    1.41
     perdida
    1.20
    Activations Density 0.009%

    No Known Activations