© 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. 26704
    Prev
    Next
    INDEX
    Explanations

    references to player positions and starter status in sports contexts

    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
    ]").
    -0.67
     useEffect
    -0.61
    ILERS
    -0.57
    Прият
    -0.56
    zepam
    -0.56
    harp
    -0.56
     Funnel
    -0.55
    čů
    -0.55
     Cougar
    -0.55
    informe
    -0.54
    POSITIVE LOGITS
     estekak
    0.65
    bootstrapcdn
    0.56
    TemporalType
    0.56
    DockStyle
    0.55
    WebServlet
    0.55
    AutoScaleMode
    0.55
     Audiodateien
    0.53
    makeConstraints
    0.52
    MENAFN
    0.52
    IMPORTED
    0.51
    Activations Density 0.008%

    No Known Activations