© 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. 130244
    Prev
    Next
    INDEX
    Explanations

    declaring integer variables

    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
     from
    -0.09
     retrieves
    -0.08
     ACTIVITIES
    -0.07
    兩種
    -0.06
     razem
    -0.06
     activates
    -0.06
     retrieve
    -0.06
    लेला
    -0.06
     produces
    -0.06
     achieves
    -0.06
    POSITIVE LOGITS
    è
    0.07
     pillars
    0.06
     pillar
    0.06
     many
    0.06
     very
    0.06
    âtre
    0.06
    welcome
    0.06
     everybody
    0.06
    notice
    0.06
    ;
    0.06
    Activations Density 0.008%

    No Known Activations