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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15409
    Prev
    Next
    INDEX
    Explanations

    patterns of structured or repetitive symbols indicating high levels of emphasis or emphasis-like features

    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
     дописавши
    -0.72
     defStyle
    -0.67
    下载附件
    -0.66
     EconPapers
    -0.63
    <!--[
    -0.62
    الحياه
    -0.61
    Expedia
    -0.58
    enterOuterAlt
    -0.57
     INTERESAR
    -0.57
    abestanden
    -0.56
    POSITIVE LOGITS
     ------
    2.31
     ,,
    0.60
    StateToProps
    0.59
    Inggris
    0.57
    azgo
    0.57
    GLA
    0.56
     GLA
    0.54
    kään
    0.54
     GSC
    0.53
    NGC
    0.53
    Activations Density 0.001%

    No Known Activations