© 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. 130962
    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
     in
    -0.07
    BUILD
    -0.06
    ClassLoader
    -0.06
     registers
    -0.06
     fairly
    -0.06
     conforms
    -0.06
     minority
    -0.06
     suspected
    -0.06
     presumed
    -0.06
     legitimacy
    -0.06
    POSITIVE LOGITS
    泛
    0.06
     ਮੁ
    0.06
     Stewart
    0.06
     वस
    0.06
    只有
    0.05
    晚上
    0.05
     दल
    0.05
     тра
    0.05
     избра
    0.05
     anything
    0.05
    Activations Density 0.000%

    No Known Activations