© 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. 129964
    Prev
    Next
    INDEX
    Explanations

    set theory questions involving mathematical notation

    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
     defect
    -0.06
     পুরুষ
    -0.06
     depan
    -0.06
     앞에서
    -0.05
    facing
    -0.05
     Athenians
    -0.05
     discharge
    -0.05
    voor
    -0.05
     resistant
    -0.05
     कैश
    -0.05
    POSITIVE LOGITS
    数据的
    0.07
     Nutzung
    0.06
     VON
    0.06
    適切な
    0.06
    高端
    0.06
    微微
    0.06
    crawler
    0.06
     inexplic
    0.06
     reutil
    0.06
    略
    0.06
    Activations Density 0.013%

    No Known Activations