© 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. 118816
    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
     CONTROL
    -0.05
    mason
    -0.05
    ∅
    -0.05
    ằng
    -0.05
    WEB
    -0.05
    坪
    -0.05
     দিতেন
    -0.05
     medir
    -0.05
    ാരം
    -0.05
     periodical
    -0.05
    POSITIVE LOGITS
     questa
    0.08
     ज्यादातर
    0.07
     futuro
    0.07
     भविष्य
    0.07
     vše
    0.07
     কি
    0.07
     seperate
    0.07
    豇
    0.06
     नहीं
    0.06
     نہیں
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.