© 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. 24779
    Prev
    Next
    INDEX
    Explanations

    references to locations and organizations, specifically in Shanghai and Beijing

    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
     Schwert
    -0.65
     sû
    -0.63
     Chancery
    -0.63
     Sopho
    -0.63
     Throne
    -0.62
     Hano
    -0.60
     Osp
    -0.59
     estudian
    -0.59
     Lent
    -0.58
    Scrolled
    -0.58
    POSITIVE LOGITS
     виправивши
    0.69
    hejiang
    0.65
    ValueStyle
    0.62
     متعلقه
    0.61
    UserScript
    0.60
     Paglinawan
    0.59
    }{*}{
    0.59
     cherchés
    0.57
     \%$\\
    0.57
    )"),
    0.57
    Activations Density 0.006%

    No Known Activations