© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20590
    Prev
    Next
    INDEX
    Explanations

    terms related to offensive and defensive lines in sports contexts, particularly football

    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
    Negative Logits
     ujednoznacz
    -0.85
     متعلقه
    -0.82
     intptr
    -0.76
    彡
    -0.73
     ویکی‌پدی
    -0.72
    writeFieldEnd
    -0.70
    MemoryWarning
    -0.70
    Hochspringen
    -0.70
    __':
    -0.64
    TemporalType
    -0.64
    POSITIVE LOGITS
     offense
    0.71
     Offense
    0.70
     Sodom
    0.68
     offensi
    0.65
     offensively
    0.65
     offensive
    0.64
    Offensive
    0.63
     Offensive
    0.63
     strikers
    0.62
     Offen
    0.59
    Activations Density 0.005%

    No Known Activations