© 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. 6019
    Prev
    Next
    INDEX
    Explanations

    references to the WX group in technical documentation

    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
    存于互联网档案馆
    -0.94
    abestanden
    -0.88
    racene
    -0.85
    CloseOperation
    -0.81
    ChromeDriver
    -0.81
    altham
    -0.81
    RenderAtEndOf
    -0.81
    stridium
    -0.79
    findpost
    -0.78
    Dill
    -0.78
    POSITIVE LOGITS
     wx
    1.84
    wx
    1.83
     WX
    0.98
    WX
    0.97
    Wx
    0.90
     Wx
    0.80
    EVT
    0.75
    小程序
    0.67
     Weih
    0.60
     شر
    0.59
    Activations Density 0.001%

    No Known Activations