© 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. 129854
    Prev
    Next
    INDEX
    Explanations

    financial and business words

    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
     exemplar
    -0.07
    Teaching
    -0.07
     संग्रह
    -0.07
     classics
    -0.07
     komunitas
    -0.06
     curated
    -0.06
     moderately
    -0.06
     Observed
    -0.06
     Teaching
    -0.06
     Severe
    -0.06
    POSITIVE LOGITS
     financial
    0.10
     financier
    0.10
     investors
    0.09
     부동산
    0.09
     investor
    0.08
     финансо
    0.08
     financières
    0.08
     financiera
    0.08
     financing
    0.08
     financially
    0.07
    Activations Density 0.013%

    No Known Activations