© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130841
    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
    makes
    -0.05
    ufs
    -0.05
    unc
    -0.05
    ...
    -0.05
    向
    -0.05
     dire
    -0.05
     주장
    -0.05
    ui
    -0.05
    broken
    -0.05
     Dire
    -0.05
    POSITIVE LOGITS
    频繁
    0.07
    因此
    0.07
    ⁶
    0.06
    ИН
    0.06
     servicemen
    0.06
    kowych
    0.06
     därför
    0.06
     анализа
    0.06
    kowe
    0.06
    Ტ
    0.06
    Activations Density 0.000%

    No Known Activations