© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130176
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缺点
    -0.06
     כמו
    -0.06
    介绍
    -0.06
     như
    -0.06
     Introdu
    -0.06
     introduction
    -0.06
     introdu
    -0.06
     مانند
    -0.05
     doesn
    -0.05
    Bea
    -0.05
    POSITIVE LOGITS
    σα
    0.07
     assessing
    0.06
     pertaining
    0.06
     programação
    0.06
    ന്ദ്ര
    0.06
    ിച്ച്
    0.06
     extravagant
    0.06
    㮔
    0.06
     훨씬
    0.06
     figuring
    0.06
    Activations Density 0.000%

    No Known Activations