© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    words that could be parts of scientific or proper names including abbreviations for any of those things

    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
     وتسجيلات
    -1.00
    ValueGeneration
    -0.96
     Olds
    -0.94
    ьаж
    -0.92
     PTS
    -0.91
     Rul
    -0.90
     ***!
    -0.88
     Alden
    -0.88
     typewriter
    -0.86
    entile
    -0.86
    POSITIVE LOGITS
     Brito
    0.94
     Doherty
    0.88
     tras
    0.75
     Alpen
    0.75
    ρ
    0.70
     Frans
    0.69
    DispatchToProps
    0.69
    م
    0.68
     Bou
    0.67
     CAA
    0.67
    Activations Density 5.584%

    No Known Activations