© 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. 129745
    Prev
    Next
    INDEX
    Explanations

    auto

    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
     generic
    -0.08
     imprecise
    -0.07
     getRandom
    -0.07
     gegevens
    -0.07
     유사
    -0.06
     Everyday
    -0.06
     interessi
    -0.06
     rudimentary
    -0.06
     standaard
    -0.06
     यदि
    -0.06
    POSITIVE LOGITS
     nipp
    0.06
     with
    0.05
     महम
    0.05
     অন্যতম
    0.05
    trem
    0.05
    lies
    0.05
     চ্যানেল
    0.05
     most
    0.05
     strongly
    0.05
    ĵo
    0.05
    Activations Density 0.002%

    No Known Activations