© 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. 130958
    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
     drugim
    -0.06
    <0xA1>
    -0.06
     দিচ্ছে
    -0.06
    以及
    -0.06
     있으며
    -0.06
     hagas
    -0.06
     Doing
    -0.05
    ގ
    -0.05
     препара
    -0.05
    מיד
    -0.05
    POSITIVE LOGITS
     эффект
    0.06
     breastfeeding
    0.06
     offen
    0.06
     সত্য
    0.06
     Ideal
    0.06
     খুবই
    0.06
     ആദ്യം
    0.06
    耧
    0.06
     पहिला
    0.05
     diamante
    0.05
    Activations Density 0.000%

    No Known Activations