© 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. 15390
    Prev
    Next
    INDEX
    Explanations

    instances of the word "though."

    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
     PLW
    -0.76
     Hald
    -0.75
     Merz
    -0.71
    makeConstraints
    -0.71
    enlace
    -0.71
    hematical
    -0.70
     rejoicing
    -0.70
    mappedBy
    -0.69
     Lur
    -0.69
     Tj
    -0.69
    POSITIVE LOGITS
     تانيه
    0.82
    '])->
    0.80
    aughan
    0.74
    optString
    0.71
     Wynne
    0.68
     }}"></
    0.67
    TypedValue
    0.66
     Phipps
    0.65
     sī
    0.65
     Woodbridge
    0.65
    Activations Density 0.011%

    No Known Activations