© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5589
    Prev
    Next
    INDEX
    Explanations

    references to specific yardage measurements related to football plays

    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
    featureID
    -0.91
     cref
    -0.79
    astify
    -0.66
     Spinoza
    -0.65
    TagMode
    -0.63
    RTLD
    -0.63
     PLWABN
    -0.62
    sleepy
    -0.61
     cherchés
    -0.60
    DockStyle
    -0.60
    POSITIVE LOGITS
     yards
    3.23
    yard
    3.19
     yard
    3.11
    yards
    2.83
     Yard
    2.78
     Yards
    2.73
    Yard
    2.70
    YARD
    2.39
     yds
    1.58
     backyard
    1.38
    Activations Density 0.006%

    No Known Activations