© 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. 20386
    Prev
    Next
    INDEX
    Explanations

    the word "this" in various contexts throughout the text

    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
    AndEndTag
    -0.95
    ChildScrollView
    -0.93
    رشف
    -0.82
    CloseOperation
    -0.80
     Paglinawan
    -0.79
     noDo
    -0.76
    DockStyle
    -0.76
     ſtate
    -0.75
     pleaſure
    -0.75
    MigrationBuilder
    -0.75
    POSITIVE LOGITS
     him
    0.49
     brand
    0.46
     Drew
    0.40
    ضا
    0.40
     وسلم
    0.38
     μέ
    0.38
    gag
    0.38
     Mid
    0.37
     
    0.37
     sure
    0.37
    Activations Density 0.003%

    No Known Activations