© 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. 27049
    Prev
    Next
    INDEX
    Explanations

    pronouns that signify perspective or emphasis in statements

    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
     [
    -0.63
     the
    -0.52
     {
    -0.51
    ↵↵
    -0.50
     taking
    -0.50
     lemb
    -0.50
     लेकर
    -0.50
     my
    -0.50
    {
    -0.49
    cham
    -0.49
    POSITIVE LOGITS
    abestanden
    1.14
     Мексичка
    1.11
    Geplaatst
    0.99
    expandindo
    0.99
    kloped
    0.96
     itſelf
    0.93
    ConstraintMaker
    0.86
     незавершена
    0.85
     Chwiliwch
    0.84
    GEBURTSDATUM
    0.84
    Activations Density 0.023%

    No Known Activations