© 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. 130469
    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
     almost
    -0.07
    engineering
    -0.07
     virtually
    -0.06
     both
    -0.06
     bijna
    -0.06
     
    -0.06
     Engineering
    -0.06
     engineering
    -0.06
     nearly
    -0.06
     eight
    -0.06
    POSITIVE LOGITS
     ninguém
    0.07
     rundown
    0.06
    otine
    0.06
    xtime
    0.06
     workspace
    0.06
    ophyte
    0.06
     도움
    0.06
     Überblick
    0.06
     durch
    0.06
    म्यान
    0.06
    Activations Density 0.000%

    No Known Activations