© 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. 6521
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals involved in combat sports or martial arts

    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
    ignements
    -0.61
    ագրություններ
    -0.52
    yl
    -0.51
    asă
    -0.51
    ée
    -0.49
    iss
    -0.48
    one
    -0.48
    vedať
    -0.48
    ana
    -0.48
    afford
    -0.48
    POSITIVE LOGITS
    RunAsync
    0.71
     ISNI
    0.63
    ustimmung
    0.63
    DebuggerNonUser
    0.61
    interprétation
    0.61
    enregistrement
    0.60
    izop
    0.59
    doria
    0.58
    hasia
    0.58
    Personendaten
    0.56
    Activations Density 0.821%

    No Known Activations