© 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. 24848
    Prev
    Next
    INDEX
    Explanations

    references to railways or railroads

    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
    argb
    -0.69
    fromCharCode
    -0.69
    MeasureSpec
    -0.68
     asum
    -0.64
     diarias
    -0.64
    Captor
    -0.63
    piram
    -0.63
    vdash
    -0.62
    ziv
    -0.61
     Rina
    -0.59
    POSITIVE LOGITS
     railway
    1.36
     railways
    1.28
    railway
    1.23
    Railway
    1.22
     Railway
    1.21
     railroad
    1.19
     railroads
    1.19
     Railways
    1.14
     Railroad
    1.13
     RAILWAY
    1.08
    Activations Density 0.009%

    No Known Activations