© 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. 20602
    Prev
    Next
    INDEX
    Explanations

    references to the word "my" in various contexts

    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
     post
    -0.58
    endum
    -0.57
     Patrick
    -0.55
     "
    -0.53
     per
    -0.51
    acio
    -0.51
    menta
    -0.50
     pre
    -0.50
     ab
    -0.49
     паспорт
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.97
     myſelf
    0.90
     متعلقه
    0.88
    expandindo
    0.87
    abestanden
    0.81
     CreateTagHelper
    0.80
     ་་
    0.80
     Chwiliwch
    0.79
    TypedDataSet
    0.76
    EDEFAULT
    0.75
    Activations Density 0.013%

    No Known Activations