© 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. 6414
    Prev
    Next
    INDEX
    Explanations

    comparisons of the degree or extent of a characteristic

    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
    __;
    -0.61
    ViewImports
    -0.60
     Wikimedijinoj
    -0.59
    IsMutable
    -0.57
    UpInside
    -0.57
     AssemblyTitle
    -0.56
    aptation
    -0.55
    
    -0.55
    ainville
    -0.53
    miede
    -0.52
    POSITIVE LOGITS
    الدراسه
    0.66
    hichever
    0.57
    請繼續往下閱讀
    0.51
     whichever
    0.50
    Whatever
    0.48
     αυτά
    0.48
    SizeF
    0.47
     apprécié
    0.47
    quanto
    0.47
     TextAlign
    0.46
    Activations Density 0.035%

    No Known Activations