© 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. 3552
    Prev
    Next
    INDEX
    Explanations

    references to football plays, specifically scoring passes and touchdowns

    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
     LOGGER
    -0.52
     JADX
    -0.50
    PerformLayout
    -0.49
    astify
    -0.49
     Mö
    -0.49
    MemoryWarning
    -0.49
    лья
    -0.48
    rather
    -0.47
     SafeMath
    -0.45
    makeConstraints
    -0.45
    POSITIVE LOGITS
     NFL
    0.77
    🏈
    0.71
    NFL
    0.67
    FormTagHelper
    0.66
    quiao
    0.63
    WithIOException
    0.63
    ADELPHIA
    0.63
     архивлан
    0.62
    TIMORE
    0.61
    styleType
    0.60
    Activations Density 0.300%

    No Known Activations