© 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. 118168
    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
    繼續
    -0.07
     거의
    -0.07
     bijna
    -0.07
     tự
    -0.07
     multid
    -0.06
     Secure
    -0.06
     этих
    -0.06
     самостоятельно
    -0.06
     continue
    -0.06
     почти
    -0.06
    POSITIVE LOGITS
     business
    0.06
    YSIS
    0.06
    最高
    0.06
     product
    0.06
    的气
    0.06
     DESIGN
    0.06
    کر
    0.06
    developers
    0.06
     design
    0.05
     商品
    0.05
    Activations Density 0.000%

    No Known Activations