© 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. 1-RES-MATRYOSHKA-DC
    7. 580
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles

    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
     材料
    -0.56
    …~
    -0.53
    nexpected
    -0.53
    materials
    -0.51
    szönöm
    -0.50
     opérés
    -0.50
    PointerException
    -0.49
    notation
    -0.49
    setCellValue
    -0.48
    Jegyzetek
    -0.48
    POSITIVE LOGITS
     article
    4.50
     Article
    3.86
    Article
    3.81
    article
    3.81
     articles
    3.78
     ARTICLE
    3.36
     Articles
    3.34
    articles
    3.17
    Articles
    3.17
    ARTICLE
    3.09
    Activations Density 0.020%

    No Known Activations