© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20316
    Prev
    Next
    INDEX
    Explanations

    terms related to glucose and its derivatives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ValueStyle
    -1.31
     jLabel
    -1.00
    DockStyle
    -0.96
    #
    -0.95
    twimg
    -0.95
    AutoScaleMode
    -0.93
     مشين
    -0.92
    GenerationType
    -0.90
    emang
    -0.90
     Rover
    -0.86
    POSITIVE LOGITS
     Glu
    1.41
     glu
    1.40
    Glu
    1.36
    glu
    1.20
     gluing
    0.82
     Glue
    0.81
     glue
    0.75
    Glue
    0.73
     glutamate
    0.71
     gluta
    0.70
    Activations Density 0.011%

    No Known Activations