© 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. 24-RES-MATRYOSHKA-DC
    7. 1582
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to competitive fights with a focus on weight

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    WriteLiteral
    -0.65
    プレー
    -0.59
     fört
    -0.54
    +#+
    -0.53
     समीक्षाएं
    -0.52
     Tugas
    -0.52
    ={({
    -0.52
     Psal
    -0.51
    ớt
    -0.51
    minde
    -0.50
    POSITIVE LOGITS
     fighters
    1.03
     fight
    1.02
     fights
    0.95
     Mayweather
    0.94
     boxing
    0.92
     UFC
    0.92
     fighter
    0.91
     Fight
    0.85
     rematch
    0.85
    fight
    0.82
    Activations Density 0.170%

    No Known Activations