© 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. 32597
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strike" and its various forms

    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
    fael
    -0.81
    vrouw
    -0.75
    cault
    -0.74
    antd
    -0.73
    DbType
    -0.71
     consequ
    -0.67
    tabol
    -0.67
     BorderRadius
    -0.67
     Bessie
    -0.66
    mybatisplus
    -0.66
    POSITIVE LOGITS
     Strikes
    1.24
     strikes
    1.23
     strike
    1.22
     Strike
    1.20
    Strike
    1.16
    strike
    1.05
     striking
    0.97
     Striking
    0.90
     Stripes
    0.88
     struck
    0.87
    Activations Density 0.009%

    No Known Activations