© 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. 118897
    Prev
    Next
    INDEX
    Explanations

    math expressions with sqrt

    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
     nunca
    -0.07
    五十
    -0.06
     never
    -0.06
     никогда
    -0.06
     último
    -0.06
    हरु
    -0.06
     nigdy
    -0.06
    szyst
    -0.06
    irlos
    -0.06
     Все
    -0.05
    POSITIVE LOGITS
    別の
    0.07
     lieber
    0.06
     amidst
    0.06
    最初は
    0.06
     다른
    0.06
    discipline
    0.06
     персонала
    0.06
     பரபர
    0.06
     direta
    0.06
    .<
    0.05
    Activations Density 0.003%

    No Known Activations