© 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. 130334
    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
     prevents
    -0.06
     वर्तमान
    -0.06
     what
    -0.06
     provides
    -0.06
    helps
    -0.06
     dapat
    -0.06
     helps
    -0.06
     Doesn
    -0.06
    What
    -0.06
     and
    -0.06
    POSITIVE LOGITS
     jedynie
    0.07
     માત્ર
    0.07
    offset
    0.06
     গোষ্ঠী
    0.06
     فقط
    0.06
     Abyss
    0.06
    的变化
    0.06
     다만
    0.06
     spazi
    0.06
    ADDRESS
    0.06
    Activations Density 0.000%

    No Known Activations