© 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. 21022
    Prev
    Next
    INDEX
    Explanations

    terms related to 'station' and 'stationery'

    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
     Eri
    -0.76
     Chaco
    -0.73
    ImageContext
    -0.73
     Prag
    -0.72
     Rift
    -0.72
    dibles
    -0.72
     Mahindra
    -0.71
     Imper
    -0.69
    ieras
    -0.66
    RIM
    -0.65
    POSITIVE LOGITS
     stations
    1.57
     Stations
    1.52
    Stations
    1.46
     Station
    1.42
     station
    1.40
    stations
    1.38
     STATION
    1.35
    Station
    1.29
    STATION
    1.24
    station
    1.17
    Activations Density 0.013%

    No Known Activations