© 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. 0-RES-MATRYOSHKA-DC
    7. 10550
    Prev
    Next
    INDEX
    Explanations

    questions about details or specifics

    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
     This
    -0.54
    '
    -0.50
    who
    -0.46
     The
    -0.45
    ouder
    -0.43
     They
    -0.43
     segíts
    -0.43
    UIAlert
    -0.43
     kereszt
    -0.42
    XCTAssert
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
    contentLoaded
    0.77
    يميديا
    0.76
    UrlResolution
    0.76
    первых
    0.73
    aughey
    0.71
    érêt
    0.69
    SequentialGroup
    0.69
    ]),
    0.68
    anthin
    0.67
    Activations Density 0.032%

    No Known Activations