© 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. 118828
    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
    ucidation
    -0.06
     stále
    -0.06
     دا
    -0.06
    seriously
    -0.06
    Prev
    -0.06
     قائم
    -0.06
    Previously
    -0.06
    लाइन
    -0.06
     creamy
    -0.06
     chy
    -0.05
    POSITIVE LOGITS
     නමුත්
    0.06
     avoiding
    0.06
     সম্ভাব্য
    0.06
    更多
    0.06
     but
    0.06
     maximize
    0.06
     đổi
    0.06
    更多的
    0.06
    主な
    0.06
     избежать
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.