© 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. 17071
    Prev
    Next
    INDEX
    Explanations

    the word "begin" and its variations, indicating the initiation of actions or processes

    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
    ScreenState
    -0.77
     Lotte
    -0.76
    MathML
    -0.75
     gyhoeddwyd
    -0.75
    UTERS
    -0.74
    ứt
    -0.71
     Sard
    -0.71
    START
    -0.70
    gerald
    -0.70
     Sart
    -0.69
    POSITIVE LOGITS
    stdbool
    0.82
    Dana
    0.81
     GIP
    0.77
     brie
    0.75
     boletos
    0.75
     Beasley
    0.74
    Brie
    0.73
     Dana
    0.73
     Brie
    0.72
     Kelley
    0.72
    Activations Density 0.019%

    No Known Activations