© 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. 29800
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and their context in relation to names and places

    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
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.77
    esModule
    -0.73
    例句
    -0.73
     abbildung
    -0.66
     sayfas
    -0.64
     länder
    -0.64
    详细信息
    -0.63
    jsxFileName
    -0.62
    unsqueeze
    -0.60
     symboles
    -0.59
    POSITIVE LOGITS
     Winding
    0.64
    Phân
    0.63
     Rip
    0.60
     tri
    0.59
    الدراسه
    0.58
     winding
    0.58
    WebServlet
    0.58
     trans
    0.57
    mord
    0.57
     getF
    0.57
    Activations Density 0.010%

    No Known Activations