© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15677
    Prev
    Next
    INDEX
    Explanations

    snippets of code or references to figures in documents

    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
     Wiktionnaire
    -0.64
    ètement
    -0.61
    rags
    -0.57
    óng
    -0.56
     Figures
    -0.55
     lampa
    -0.55
     hereof
    -0.55
     Theſe
    -0.54
     상세
    -0.54
     folks
    -0.54
    POSITIVE LOGITS
    figure
    2.08
    findpost
    0.72
    jooq
    0.62
    picture
    0.60
    SpringBootTest
    0.59
    stylesheet
    0.58
    figured
    0.54
     arbeid
    0.54
    cuadro
    0.53
    ttino
    0.52
    Activations Density 0.001%

    No Known Activations