© 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. 119755
    Prev
    Next
    INDEX
    Explanations

    accumulates, hoarding, accumulating

    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
    希望
    -0.06
     чувстви
    -0.06
     বুঝে
    -0.06
    bestand
    -0.06
     tomorrow
    -0.05
     hopes
    -0.05
    希望能
    -0.05
     triangular
    -0.05
     tonight
    -0.05
     slightly
    -0.05
    POSITIVE LOGITS
     hoarding
    0.07
     accumulates
    0.07
     масса
    0.07
     superviv
    0.07
     accumulate
    0.07
     accumulated
    0.06
     filthy
    0.06
     prolonged
    0.06
     malnourished
    0.06
     accumulation
    0.06
    Activations Density 0.058%

    No Known Activations