© 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. 21092
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thereby."

    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
    zése
    -0.71
    listdir
    -0.68
    IsSet
    -0.67
    aroma
    -0.66
     BitmapFactory
    -0.66
     Mace
    -0.64
    Apologies
    -0.63
    Asu
    -0.62
    rildi
    -0.62
    άσ
    -0.62
    POSITIVE LOGITS
     EMB
    0.75
    InputBorder
    0.69
    rrggbb
    0.66
     thereby
    0.65
    TagHelper
    0.65
     Bem
    0.63
    orology
    0.61
     whereby
    0.60
    googleapis
    0.59
     Fonseca
    0.59
    Activations Density 0.007%

    No Known Activations