© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8433
    Prev
    Next
    INDEX
    Explanations

    terminology related to railway infrastructure and operations

    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
     Airport
    -0.62
    aéroport
    -0.60
     runway
    -0.59
    ünstler
    -0.58
    IonicModule
    -0.57
     airport
    -0.56
    papar
    -0.52
    Airport
    -0.50
     belt
    -0.50
     runways
    -0.50
    POSITIVE LOGITS
     locomotives
    0.85
     ferrovi
    0.74
     Locomotive
    0.73
     المعيارى
    0.73
     Roskov
    0.71
    RAIL
    0.70
     locomotive
    0.69
     Trains
    0.69
    Trains
    0.68
    Rail
    0.68
    Activations Density 0.020%

    No Known Activations