© 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. 32463
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their structures in a web document

    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
     Picchu
    -0.48
     läuft
    -0.45
     erop
    -0.44
    Clik
    -0.43
     dụ
    -0.42
     Pab
    -0.41
    timiento
    -0.41
    low
    -0.41
     opérations
    -0.41
     kise
    -0.41
    POSITIVE LOGITS
     propOrder
    0.73
     autorytatywna
    0.69
    ValueGeneration
    0.68
    ➟
    0.65
    +#+
    0.61
    verwijspagina
    0.61
     ModelExpression
    0.60
    StartTag
    0.59
    buttonShape
    0.59
    Izvori
    0.58
    Activations Density 0.011%

    No Known Activations