© 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. 119046
    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
    lerinden
    -0.07
    Invariant
    -0.06
     предлагают
    -0.06
     with
    -0.05
    திலும்
    -0.05
     drinkers
    -0.05
     með
    -0.05
     दुर्भाग्य
    -0.05
    ल्ज
    -0.05
     vaak
    -0.05
    POSITIVE LOGITS
     was
    0.07
     आवाज
    0.06
     poteva
    0.06
     mushrooms
    0.06
     puisqu
    0.06
     downregulation
    0.06
     संस्थापक
    0.06
     grammaticality
    0.06
     pharmaceuticals
    0.06
    het
    0.06
    Activations Density 0.000%

    No Known Activations