© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4826
    Prev
    Next
    INDEX
    Explanations

    references to sports appearances, debuts, and specific events in athletic careers

    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
     />);
    -0.57
    ابل
    -0.57
    cenario
    -0.55
    MENAFN
    -0.55
    mogat
    -0.54
    principalTable
    -0.54
     alarme
    -0.53
     frågan
    -0.52
     imagin
    -0.52
     spontan
    -0.51
    POSITIVE LOGITS
     stint
    1.07
     tenure
    1.02
     Tenure
    0.85
     sojourn
    0.84
     career
    0.77
     apprenticeship
    0.71
     biography
    0.70
    Tenure
    0.70
     residence
    0.69
     seniority
    0.69
    Activations Density 1.410%

    No Known Activations