© 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. 23377
    Prev
    Next
    INDEX
    Explanations

    references to ownership, specifically using pronouns like "our" and "my."

    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
    contentLoaded
    -0.56
     jugé
    -0.54
    if
    -0.52
     gevo
    -0.52
     placas
    -0.52
    RefNanny
    -0.51
    aspetto
    -0.51
    textAppearance
    -0.50
     fuis
    -0.50
    Amid
    -0.49
    POSITIVE LOGITS
     EconPapers
    1.05
    gonic
    0.95
     незавершена
    0.77
    gheny
    0.73
     focus
    0.73
     goal
    0.73
    yssey
    0.71
    iastes
    0.71
    roek
    0.71
    WebServlet
    0.70
    Activations Density 0.031%

    No Known Activations