© 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. 0-RES-MATRYOSHKA-DC
    7. 11779
    Prev
    Next
    INDEX
    Explanations

    references to configuration files or settings within code snippets

    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
     صوتيه
    -0.60
    |}{$
    -0.58
    LayoutStyle
    -0.56
    TintMode
    -0.56
     Algon
    -0.54
     consultato
    -0.54
     preparare
    -0.54
     localObject
    -0.54
    Numerology
    -0.53
     configuring
    -0.53
    POSITIVE LOGITS
    cfg
    2.78
     cfg
    1.92
    Cfg
    1.47
    CFG
    1.27
     CFG
    0.76
    міністра
    0.59
    shutil
    0.58
    manteau
    0.55
     BrowserModule
    0.54
    XCTAssert
    0.53
    Activations Density 0.001%

    No Known Activations