© 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. 9223
    Prev
    Next
    INDEX
    Explanations

    mathematical structures or relationships in data representation

    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
    principalTable
    -0.59
    tinyos
    -0.54
    ValueStyle
    -0.50
     McRae
    -0.48
    initComponents
    -0.44
    MENAFN
    -0.43
    AntiForgeryToken
    -0.42
    тони
    -0.42
    BASELINE
    -0.41
     kereszt
    -0.39
    POSITIVE LOGITS
     estekak
    0.77
    balleur
    0.67
     ainfi
    0.67
    buttonBar
    0.66
     ModelRenderer
    0.65
    seamnă
    0.63
    RTEX
    0.63
    UpInside
    0.63
     refusé
    0.61
    omeness
    0.60
    Activations Density 0.033%

    No Known Activations