© 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-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7144
    Prev
    Next
    INDEX
    Explanations

    references to the chemical compound glucose

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.77
    aarrggbb
    -0.67
    ViewFeatures
    -0.65
    cero
    -0.64
     CreateTagHelper
    -0.63
     patro
    -0.62
     bero
    -0.61
     Hark
    -0.61
     Org
    -0.59
    fiche
    -0.58
    POSITIVE LOGITS
    glu
    3.13
    Glu
    3.06
     Glu
    2.91
     glu
    2.75
     gluing
    1.56
     gluon
    1.55
     gluta
    1.52
     glutamate
    1.50
     glued
    1.38
     glue
    1.34
    Activations Density 0.013%

    No Known Activations