© 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. 2-RES-MATRYOSHKA-DC
    7. 6413
    Prev
    Next
    INDEX
    Explanations

    code snippets related to managing storage or variables

    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
    Diweddarwch
    -0.72
    mobileqq
    -0.67
     كومونز
    -0.65
    rupulous
    -0.63
    expandindo
    -0.63
    Preamble
    -0.63
    存于互联网档案馆
    -0.61
    ülete
    -0.60
    IActionResult
    -0.60
     समीक्षाओं
    -0.58
    POSITIVE LOGITS
    args
    3.25
     args
    2.92
    Args
    1.95
     Args
    1.67
    ARGS
    1.35
    argv
    0.91
    nargs
    0.81
     Arg
    0.81
     argv
    0.81
     arg
    0.79
    Activations Density 0.003%

    No Known Activations