© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15680
    Prev
    Next
    INDEX
    Explanations

    instances of the text pattern depicting a single quote followed by an opening parenthesis, indicating a focus on identifying specific types of quoted or parenthesized expressions

    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
    bootstrapcdn
    -0.72
     समीक्षाओं
    -0.67
     مواليد
    -0.66
    ViewFeatures
    -0.64
    .--
    -0.62
     الرياضيه
    -0.60
    expandindo
    -0.60
    лтамалар
    -0.59
     $__
    -0.57
    meal
    -0.57
    POSITIVE LOGITS
    '(
    2.34
    "(
    0.94
     '(
    0.94
    minecraftforge
    0.63
    '[
    0.62
    ^{*}(
    0.59
    ”(
    0.57
     "(
    0.56
    ddots
    0.55
    ("(
    0.54
    Activations Density 0.001%

    No Known Activations