© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15591
    Prev
    Next
    INDEX
    Explanations

    references to data or information sources, particularly instances starting with "The" or "This" indicating references to documented data or documentation

    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
     AssemblyCompany
    -0.79
     betweenstory
    -0.78
    CompilerServices
    -0.77
     дописавши
    -0.75
    AutoresizingMask
    -0.74
     MainAxisSize
    -0.73
    AndEndTag
    -0.73
     Италијани
    -0.73
    LLocation
    -0.70
    MethodManager
    -0.70
    POSITIVE LOGITS
    例文帳に追加
    0.55
    ่วม
    0.53
    FieldNumber
    0.53
    ISSN
    0.52
    」。
    0.52
    </code>
    0.49
     même
    0.48
    urn
    0.47
    』。
    0.47
    jface
    0.47
    Activations Density 0.299%

    No Known Activations