© 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. 7610
    Prev
    Next
    INDEX
    Explanations

    if a particular numerical value related to loss exceeds a certain threshold

    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
     winning
    -1.58
     Winning
    -1.45
    Winning
    -1.38
    winning
    -1.31
     wins
    -1.24
     win
    -1.14
    wins
    -1.04
     winnings
    -1.03
     winners
    -1.02
     vincere
    -1.02
    POSITIVE LOGITS
     loss
    1.78
    loss
    1.64
     Loss
    1.63
    Loss
    1.52
     LOSS
    1.36
    LOSS
    1.16
     perte
    1.00
     losses
    0.88
     pérdida
    0.87
    losses
    0.87
    Activations Density 0.053%

    No Known Activations