© 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. 105
    Prev
    Next
    INDEX
    Explanations

    a pattern of symbols, characters, or formatting elements

    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
     trekken
    -0.82
     CreateTagHelper
    -0.77
    complexContent
    -0.69
     AssemblyCulture
    -0.68
    PointerException
    -0.68
     paramInt
    -0.68
    MigrationBuilder
    -0.66
     uttered
    -0.66
     SPECIES
    -0.66
    assertj
    -0.66
    POSITIVE LOGITS
     service
    1.20
     facilities
    1.17
     services
    1.16
     ſche
    1.15
     houſe
    1.08
    service
    0.95
     program
    0.94
     business
    0.94
     servicing
    0.94
     ſch
    0.93
    Activations Density 16.630%

    No Known Activations