© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12806
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific pattern or element, particularly related to "replacements" in code or text processing contexts

    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
    ment
    -1.02
     Ment
    -0.73
    MENT
    -0.69
     فريبيس
    -0.60
     MENT
    -0.60
    NameInMap
    -0.59
    Ment
    -0.57
     مرئيه
    -0.57
     المعيارى
    -0.57
    andum
    -0.56
    POSITIVE LOGITS
    ments
    2.13
    MENTS
    1.10
    EMENTS
    0.77
    下载附件
    0.60
     ments
    0.58
    reportWebVitals
    0.56
     Kä
    0.55
    eseorang
    0.54
    脚注の使い方
    0.53
     Itália
    0.53
    Activations Density 0.002%

    No Known Activations