© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130932
    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
    Browse
    -0.07
     डॉक्यूमेंट
    -0.06
     currents
    -0.06
     meist
    -0.06
     máximo
    -0.05
     browse
    -0.05
     browsing
    -0.05
     máxim
    -0.05
     these
    -0.05
     ultrast
    -0.05
    POSITIVE LOGITS
     শুধুমাত্র
    0.08
     دو
    0.07
     एक
    0.07
     двух
    0.07
    只有
    0.07
     for
    0.07
     ერთი
    0.07
     두
    0.07
     მხოლოდ
    0.07
     ONLY
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.