© 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. 130815
    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
    懊
    -0.06
     आवर
    -0.06
     doğru
    -0.06
     informativo
    -0.06
    ́c
    -0.06
     memberikan
    -0.06
    antic
    -0.06
     information
    -0.06
    慑
    -0.06
    alis
    -0.05
    POSITIVE LOGITS
    eynman
    0.06
     způsob
    0.06
    を使用して
    0.06
    ifadə
    0.06
     additions
    0.06
    dió
    0.06
    defence
    0.06
    रखाव
    0.06
     adjunct
    0.05
     स्थान
    0.05
    Activations Density 0.000%

    No Known Activations