© 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. 22362
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "you" and its variations in the text, indicating a focus on direct address or dialogue

    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
    your
    -0.88
    Your
    -0.75
     your
    -0.75
    TagMode
    -0.70
    EndGlobalSection
    -0.69
     initComponents
    -0.68
     Your
    -0.66
     Wiktionnaire
    -0.61
    Votre
    -0.60
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
     Feldman
    0.61
     OGSÅ
    0.57
    ▻
    0.57
    dodge
    0.57
    estroyer
    0.56
     ویکی‌پدیا
    0.55
     NUKAT
    0.54
     saja
    0.53
    WEBPACK
    0.51
    엇
    0.50
    Activations Density 0.022%

    No Known Activations