© 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. 130390
    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
     meestal
    -0.07
    迅速
    -0.06
     modern
    -0.06
     usually
    -0.06
     often
    -0.06
    都会
    -0.06
    প্ট
    -0.06
    一個
    -0.06
     보통
    -0.06
     一个
    -0.06
    POSITIVE LOGITS
     khususnya
    0.07
     it
    0.06
     தேர்
    0.06
     which
    0.06
     suggestions
    0.06
    ที่คุณ
    0.06
    했
    0.06
     higher
    0.06
     которые
    0.06
     deux
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.