© 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. 6-RES-MATRYOSHKA-DC
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    acronyms, abbreviations, and symbols

    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
    HasAnnotation
    -0.61
     BorderSide
    -0.59
    ViewImports
    -0.58
     betweenstory
    -0.58
     referrerpolicy
    -0.57
    日在
    -0.57
    روابط
    -0.56
    SourceChecksum
    -0.56
     Wicidata
    -0.55
     akong
    -0.54
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.73
     <=",
    0.62
     guise
    0.61
    文中
    0.60
    MeasureSpec
    0.60
    onViewCreated
    0.60
     préférence
    0.59
     odkazy
    0.58
     וב
    0.57
     maupun
    0.56
    Activations Density 4.349%

    No Known Activations