© 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. 130822
    Prev
    Next
    INDEX
    Explanations

    dendrimers and branched polymers

    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
     principale
    -0.07
    banding
    -0.06
     एकमात्र
    -0.06
    eleri
    -0.06
     necess
    -0.06
     fabricantes
    -0.06
     przet
    -0.06
     Resources
    -0.06
    ained
    -0.06
     Parole
    -0.06
    POSITIVE LOGITS
     completeness
    0.06
     multival
    0.06
     отсутствует
    0.06
     like
    0.06
     allotted
    0.06
     gather
    0.06
     πλή
    0.06
     aument
    0.06
    like
    0.06
     crescendo
    0.06
    Activations Density 0.009%

    No Known Activations