© 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. 118272
    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
     finalement
    -0.07
     பகி
    -0.07
    ificant
    -0.06
     znač
    -0.06
     otros
    -0.06
     सफलतापूर्वक
    -0.06
    setFont
    -0.06
     ছাড়াও
    -0.06
     Imported
    -0.06
     बर्तन
    -0.06
    POSITIVE LOGITS
     بدء
    0.06
    anga
    0.06
    即使
    0.06
     संदीप
    0.06
    agini
    0.06
     मध्य
    0.06
     строи
    0.06
     halted
    0.06
    mr
    0.05
     நடு
    0.05
    Activations Density 0.000%

    No Known Activations