© 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. 2-RES-MATRYOSHKA-DC
    7. 5782
    Prev
    Next
    INDEX
    Explanations

    references to professional wrestling and wrestlers

    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
     Theſe
    -0.90
     виправивши
    -0.79
     Beſ
    -0.75
    Portail
    -0.75
     CAI
    -0.74
     becauſe
    -0.73
    WithContext
    -0.72
     Soud
    -0.71
     whoſe
    -0.71
     Савезне
    -0.70
    POSITIVE LOGITS
     wrestling
    2.84
     Wrestling
    2.80
    Wrestling
    2.39
     wrestler
    2.38
     wrestlers
    2.28
     wrestle
    2.25
     wrestled
    2.17
    restling
    1.95
     WWE
    1.65
     wrest
    1.63
    Activations Density 0.003%

    No Known Activations