© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7621
    Prev
    Next
    INDEX
    Explanations

    references to specific numbered items or pairs, often denoted by parentheses with accompanying numbers or identifiers

    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
    Negative Logits
    RequestParam
    -0.50
    shadowOpacity
    -0.48
    ViewFeatures
    -0.48
     first
    -0.46
     tắt
    -0.45
    UALA
    -0.45
     lap
    -0.44
    unnamed
    -0.44
    toBeDefined
    -0.44
    )‏
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.83
    AccessorTable
    0.81
    رشف
    0.80
    BeginContext
    0.77
     AssemblyVersion
    0.75
    OGND
    0.75
    sizeCache
    0.73
    SharedDtor
    0.73
    Hentet
    0.69
    UnsafeEnabled
    0.68
    Activations Density 0.548%

    No Known Activations