© 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. 130994
    Prev
    Next
    INDEX
    Explanations

    options, derivatives, market, Bitcoin

    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
     has
    -0.08
     récente
    -0.06
    द्भ
    -0.06
     extends
    -0.06
     heeft
    -0.06
     recently
    -0.06
     insists
    -0.06
     accidental
    -0.06
     최근
    -0.06
     मालम
    -0.06
    POSITIVE LOGITS
    即可
    0.07
     दूस
    0.07
     دیگه
    0.07
     다섯
    0.06
     simple
    0.06
     anderen
    0.06
     senza
    0.06
     determinada
    0.06
     target
    0.06
     लाइन
    0.06
    Activations Density 0.008%

    No Known Activations