© 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. 0-RES-MATRYOSHKA-DC
    7. 12230
    Prev
    Next
    INDEX
    Explanations

    references to affidavits and instances of reflux under specific conditions

    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
    tableFuture
    -0.77
    AddTagHelper
    -0.75
    Personensuche
    -0.73
     समीक्षाओं
    -0.67
     ThreadPool
    -0.63
     jspb
    -0.60
     Geng
    -0.57
    ViewFeatures
    -0.57
    MemoryWarning
    -0.57
    Бахар
    -0.55
    POSITIVE LOGITS
     reflux
    2.55
     affidavits
    1.11
    webElementXpaths
    0.61
     poached
    0.56
    Vidi
    0.55
     xrange
    0.54
    EnableWeb
    0.52
    Rohy
    0.50
    مئ
    0.50
     gyhoeddwyd
    0.50
    Activations Density 0.001%

    No Known Activations