© 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. 25916
    Prev
    Next
    INDEX
    Explanations

    references to sports and sports-related terminology

    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
    dars
    -0.73
     Bacter
    -0.71
     Augusta
    -0.70
    Qubit
    -0.70
     Knives
    -0.68
     tabled
    -0.68
    }],
    -0.68
     curtain
    -0.67
     Ums
    -0.66
    Hentet
    -0.66
    POSITIVE LOGITS
     sports
    1.23
     Sports
    1.23
    Sports
    1.19
    sports
    1.11
     SPORTS
    1.04
     SPORT
    1.04
     Sport
    1.02
    Sport
    0.96
     deportes
    0.94
     sport
    0.92
    Activations Density 0.011%

    No Known Activations