© 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. 860
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming language keywords

    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
     d
    -0.49
     di
    -0.48
     ask
    -0.44
     i
    -0.44
     la
    -0.44
     last
    -0.44
     meant
    -0.44
    bootstrapcdn
    -0.43
    AccessFile
    -0.43
     ски
    -0.43
    POSITIVE LOGITS
    UnitTesting
    1.29
    RegressionTest
    1.05
    verifyException
    1.05
     Xunit
    1.03
    assert
    1.02
     XCTest
    0.97
    TestMethod
    0.95
    assertEqual
    0.94
    Assert
    0.93
     NUnit
    0.92
    Activations Density 1.507%

    No Known Activations