© 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. 130408
    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
     start
    -0.06
     options
    -0.06
     illet
    -0.06
    䐂
    -0.06
    দিনই
    -0.06
     nemmeno
    -0.06
     niezb
    -0.05
     Etc
    -0.05
     new
    -0.05
    の中から
    -0.05
    POSITIVE LOGITS
     أكثر
    0.08
     haben
    0.07
     время
    0.06
     arguably
    0.06
     खूप
    0.06
     admittedly
    0.06
    겠다
    0.06
     अपराध
    0.06
     بسیار
    0.06
     rheumatoid
    0.06
    Activations Density 0.000%

    No Known Activations