© 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. 118266
    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
     ہدایت
    -0.07
     any
    -0.06
     White
    -0.06
     misalkan
    -0.06
     odlu
    -0.06
    จำเป็น
    -0.06
     optimizations
    -0.06
     bloco
    -0.06
     as
    -0.06
    金属
    -0.06
    POSITIVE LOGITS
     glory
    0.06
     সাহায
    0.06
     comienzo
    0.06
     জাতিসঙ্ঘ
    0.06
     অধিকাংশই
    0.05
    गुजरात
    0.05
     சம்பந்த
    0.05
    了一个
    0.05
    шают
    0.05
     аутох
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.