© 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. 1-RES-MATRYOSHKA-DC
    7. 78
    Prev
    Next
    INDEX
    Explanations

    references to specific data points or identifiers within scientific or technical 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
    tymologie
    -0.62
    EndGlobalSection
    -0.61
     للمعارف
    -0.60
    findpost
    -0.57
     aisle
    -0.57
     فريبيس
    -0.56
     cioccolato
    -0.55
    onucleotide
    -0.55
    Gambas
    -0.54
    ownic
    -0.54
    POSITIVE LOGITS
    ref
    4.50
     ref
    3.66
    Ref
    3.66
     Ref
    3.48
    REF
    3.45
     REF
    3.13
    refs
    2.61
     refs
    2.53
    Refs
    2.48
     reference
    2.39
    Activations Density 1.344%

    No Known Activations