© 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. 11706
    Prev
    Next
    INDEX
    Explanations

    terms related to glycoproteins and their structures

    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
    NavController
    -1.16
    CodedInputStream
    -1.08
     Efq
    -1.07
    FieldBuilder
    -1.05
     ***!
    -1.00
    存于互联网档案馆
    -0.97
     Momb
    -0.96
    IBarButtonItem
    -0.94
    참고
    -0.91
    出版年
    -0.90
    POSITIVE LOGITS
     Gly
    1.75
     gly
    1.54
    Gly
    1.51
    gly
    1.16
     glyph
    1.13
    GLY
    1.01
     glycine
    0.89
    glyph
    0.88
     glycol
    0.81
    Glyph
    0.72
    Activations Density 0.022%

    No Known Activations