© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131052
    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
     estadio
    -0.07
     invierno
    -0.06
     winter
    -0.06
     Irishman
    -0.06
     inverno
    -0.06
     mapas
    -0.06
     mwaka
    -0.06
     homenaje
    -0.06
     navide
    -0.06
     maximale
    -0.06
    POSITIVE LOGITS
     khawatir
    0.06
    使用者
    0.06
    Khi
    0.06
    法律
    0.06
     counterfe
    0.06
     while
    0.06
     রশ্ম
    0.06
    欧洲
    0.06
    Когда
    0.06
     मतदारसंघात
    0.06
    Activations Density 0.003%

    No Known Activations