© 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. 117852
    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
     ferocious
    -0.08
     অত্যন্ত
    -0.08
     several
    -0.07
    ไม่มี
    -0.07
     not
    -0.07
     ridiculously
    -0.07
     tertentu
    -0.07
     unfounded
    -0.07
    ไม่
    -0.07
     ਕਰੋ
    -0.07
    POSITIVE LOGITS
    那些
    0.06
    engineering
    0.06
    但
    0.05
     डिल
    0.05
    ంటీ
    0.05
    Engineering
    0.05
     those
    0.05
    譬
    0.05
    エンジ
    0.05
     சிந்த
    0.05
    Activations Density 0.000%

    No Known Activations