© 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. 20500
    Prev
    Next
    INDEX
    Explanations

    the letter 'a' and variations of it

    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
    zte
    -0.56
    fxml
    -0.56
     للاسماء
    -0.53
    springframework
    -0.53
    GoogleApiClient
    -0.52
    ditional
    -0.52
    querySelectorAll
    -0.51
    intahan
    -0.51
    一生
    -0.50
    devServer
    -0.49
    POSITIVE LOGITS
    IUrlHelper
    0.75
    تقاوى
    0.66
     ویکی‌پدیا
    0.66
     >=",
    0.65
     himo
    0.64
    exitRule
    0.63
    writeField
    0.63
    AddTagHelper
    0.60
    piecze
    0.59
     Audiodateien
    0.59
    Activations Density 0.006%

    No Known Activations