© 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. 3-RES-MATRYOSHKA-DC
    7. 2311
    Prev
    Next
    INDEX
    Explanations

    phrases joined by the word "and" related to government, institutions, or documents.

    oai_token-act-pair · gemini-2.0-flash
    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
     critères
    -0.54
    CardModule
    -0.53
    ℗
    -0.53
    eradish
    -0.49
    ⓘ
    -0.48
    lucht
    -0.47
    фере
    -0.46
    addComponent
    -0.46
    ोजन
    -0.46
    wheel
    -0.46
    POSITIVE LOGITS
     שוליים
    0.84
    BeginContext
    0.77
    httphttps
    0.70
     snippetHide
    0.70
    UserScript
    0.69
     cherchés
    0.68
     EconPapers
    0.66
    पया
    0.65
    GEBURTSDATUM
    0.65
    IContainer
    0.63
    Activations Density 0.721%

    No Known Activations