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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15297
    Prev
    Next
    INDEX
    Explanations

    references to code documentation and descriptions of code behavior

    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
    __":
    -0.67
     समीक्षाओं
    -0.66
    Personensuche
    -0.66
     Baillargeon
    -0.65
     Normdatei
    -0.65
    SourceChecksum
    -0.65
     Италијани
    -0.62
    تفصیلات
    -0.62
    AddHtmlAttribute
    -0.61
    .*")]
    -0.60
    POSITIVE LOGITS
     describing
    1.55
    describing
    1.27
     detailing
    1.08
     explaining
    0.91
     depicting
    0.83
     characterizing
    0.78
     outlining
    0.75
     discussing
    0.66
     menggambarkan
    0.66
     portraying
    0.65
    Activations Density 0.006%

    No Known Activations