© 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. 118957
    Prev
    Next
    INDEX
    Explanations

    datetime and time formatting

    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
    하던
    -0.07
    vs
    -0.06
    เพิ่มเติม
    -0.06
    previous
    -0.06
     adicional
    -0.06
    mut
    -0.06
     डीडी
    -0.06
     टिश्यू
    -0.06
    ずつ
    -0.06
    between
    -0.05
    POSITIVE LOGITS
     gave
    0.06
     berupa
    0.06
     anún
    0.06
    曾經
    0.06
     статус
    0.06
    曾经
    0.06
     peut
    0.06
    gave
    0.06
     consequently
    0.06
     datetime
    0.06
    Activations Density 0.002%

    No Known Activations