© 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. 0-RES-MATRYOSHKA-DC
    7. 14461
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific data identifiers used in cache management and data fetching processes

    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
    KeySpec
    -0.70
     ddelweddau
    -0.65
    da
    -0.65
     contextLoads
    -0.63
     فريبيس
    -0.61
    Abitanti
    -0.60
     Pierson
    -0.58
     becauſe
    -0.56
    WidgetItem
    -0.56
    BuildContext
    -0.56
    POSITIVE LOGITS
     DA
    2.19
     dare
    0.83
     Dare
    0.67
     dared
    0.59
    Dare
    0.59
    tuta
    0.59
     dares
    0.54
    مصادر
    0.52
     Dem
    0.52
    uminense
    0.51
    Activations Density 0.001%

    No Known Activations