© 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. 12-RES-MATRYOSHKA-DC
    7. 31083
    Prev
    Next
    INDEX
    Explanations

    references to sports team structures, specifically related to rosters and player statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -1.14
    IntoConstraints
    -0.90
    ValueStyle
    -0.88
    RenderAtEndOf
    -0.88
    findpost
    -0.85
    InitVars
    -0.76
    openConnection
    -0.75
    ConstraintMaker
    -0.73
    aarrggbb
    -0.72
    awtextra
    -0.69
    POSITIVE LOGITS
    UMBUS
    0.61
     roster
    0.54
     core
    0.53
    icio
    0.49
    щина
    0.48
     constructs
    0.47
    ्रीय
    0.46
     g
    0.46
    chorus
    0.45
     construct
    0.45
    Activations Density 0.024%

    No Known Activations