© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128711
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving 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
     przez
    -0.06
     melalui
    -0.06
    through
    -0.06
     through
    -0.06
     mysterious
    -0.06
    प्रति
    -0.06
     Fisherman
    -0.06
     भने
    -0.06
     centre
    -0.05
     via
    -0.05
    POSITIVE LOGITS
     relying
    0.06
     conferring
    0.06
     следующих
    0.06
     suivi
    0.06
     진행
    0.06
     that
    0.06
    次に
    0.06
     nyug
    0.06
     капита
    0.06
     계속
    0.06
    Activations Density 0.001%

    No Known Activations