© 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. 6532
    Prev
    Next
    INDEX
    Explanations

    references to the word "win" in various capitalizations

    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
     window
    -0.80
    window
    -0.67
    GLFW
    -0.62
     Window
    -0.62
    UIView
    -0.61
    RectangleBorder
    -0.60
    WINDOW
    -0.57
    gawai
    -0.57
    adaptiveStyles
    -0.54
    ayaquil
    -0.54
    POSITIVE LOGITS
    Win
    2.80
    win
    2.72
     Win
    2.72
     win
    2.64
    WIN
    2.22
     WIN
    2.22
     wins
    1.70
    wins
    1.63
     Wins
    1.56
    Wins
    1.46
    Activations Density 0.018%

    No Known Activations