© 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. 118599
    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
     volledig
    -0.07
     vollständig
    -0.06
     innovative
    -0.06
     invented
    -0.06
     ሙሉ
    -0.06
     autrefois
    -0.06
     inventing
    -0.06
    νονται
    -0.06
     advanced
    -0.06
     আলোচ
    -0.06
    POSITIVE LOGITS
     ஆகியவற்ற
    0.07
     போன்றவற்ற
    0.06
     कलेक्शन
    0.06
     punishment
    0.06
    Affect
    0.06
    今後の
    0.06
     zapewn
    0.06
     punishments
    0.05
    ineed
    0.05
    ให้กับ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.