© 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. 118290
    Prev
    Next
    INDEX
    Explanations

    bipartite graphs and differential calculus

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     bye
    -0.06
    ستہ
    -0.05
     пропуска
    -0.05
     Somit
    -0.05
    endom
    -0.05
     Nationalism
    -0.05
     frustrated
    -0.05
    кә
    -0.05
     immersive
    -0.05
     Appear
    -0.05
    POSITIVE LOGITS
    與
    0.07
    ধরনের
    0.07
     자신
    0.07
     depuis
    0.07
     sejak
    0.07
    与
    0.06
    一百
    0.06
     их
    0.06
     jako
    0.06
     эффективность
    0.06
    Activations Density 0.001%

    No Known Activations