© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6576
    Prev
    Next
    INDEX
    Explanations

    mentions of winning or victory

    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
    Not in Any Lists

    No Comments

    Negative Logits
     loss
    -0.79
     الرياضيه
    -0.77
    loss
    -0.73
     perte
    -0.69
     perdita
    -0.66
     Verlust
    -0.66
    Loss
    -0.64
     Loss
    -0.61
    audiovisuel
    -0.59
    fromnode
    -0.59
    POSITIVE LOGITS
     won
    2.70
    Won
    2.42
     Won
    2.34
    won
    2.31
     WON
    2.17
    WON
    1.90
     winning
    1.61
     Winning
    1.43
    Winning
    1.41
     wins
    1.40
    Activations Density 0.029%

    No Known Activations