© 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. 2-RES-MATRYOSHKA-DC
    7. 6629
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technical functions or components related to code or hardware

    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
    StoryboardSegue
    -0.50
     InputDecoration
    -0.47
    DotNetBar
    -0.47
    yeti
    -0.43
     Wann
    -0.43
     LoggerFactory
    -0.41
     Extremely
    -0.40
    Extremely
    -0.40
    mergeFrom
    -0.40
    NOPQRST
    -0.39
    POSITIVE LOGITS
     <=",
    0.75
    RegressionTest
    0.71
    mayr
    0.67
    NewUrlParser
    0.65
    Архівовано
    0.64
     Catawiki
    0.62
    出版年
    0.62
    ksesta
    0.61
     nahilalakip
    0.61
    atguigu
    0.60
    Activations Density 4.233%

    No Known Activations