© 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. 17678
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Wilson

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Eich
    -0.82
     Audiodateien
    -0.80
    RefNanny
    -0.77
     Rä
    -0.73
     Ronda
    -0.73
     Meow
    -0.73
     Trang
    -0.72
     Eust
    -0.70
     Piac
    -0.70
     Epp
    -0.69
    POSITIVE LOGITS
     Wilson
    2.11
     WILSON
    1.79
    Wilson
    1.77
     Wils
    1.64
     wilson
    1.63
    wilson
    1.47
    ilson
    1.02
    WIL
    0.84
     MotionEvent
    0.77
     Timberlake
    0.75
    Activations Density 0.005%

    No Known Activations