© 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. 128501
    Prev
    Next
    INDEX
    Explanations

    self relational table or join table

    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
     pièces
    -0.06
     sources
    -0.06
     otros
    -0.06
     source
    -0.06
     lossless
    -0.06
    probable
    -0.06
     figuras
    -0.05
     baja
    -0.05
     incidents
    -0.05
     nguồn
    -0.05
    POSITIVE LOGITS
     menyes
    0.06
     مذہبی
    0.06
     mengatasi
    0.06
     बजरंग
    0.06
     intersection
    0.06
    𝚞
    0.06
     Barb
    0.06
     quantifying
    0.06
    constexpr
    0.06
     myself
    0.05
    Activations Density 0.006%

    No Known Activations