© 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. 28440
    Prev
    Next
    INDEX
    Explanations

    references to wrestling and related activities

    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
    
    -0.97
    出版年
    -0.94
     дописавши
    -0.93
     tartalomajánló
    -0.92
     newArr
    -0.91
     Rohing
    -0.90
     للمعارف
    -0.89
     leſs
    -0.89
    ^(@)
    -0.88
     ThemeData
    -0.88
    POSITIVE LOGITS
     Wrestling
    1.40
     wrestling
    1.30
    Wrestling
    1.18
     wrestle
    1.11
     wrestler
    1.03
     wrestlers
    1.02
     wrestled
    1.00
    restling
    0.98
     wrest
    0.89
    restler
    0.77
    Activations Density 0.001%

    No Known Activations