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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5721
    Prev
    Next
    INDEX
    Explanations

    references to bus and transportation terminology

    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
     flamingo
    -0.94
     Rena
    -0.89
    /−
    -0.84
    teht
    -0.82
     Sora
    -0.82
    ghen
    -0.80
     Telangana
    -0.79
     eingeb
    -0.79
     Maje
    -0.78
    eya
    -0.77
    POSITIVE LOGITS
     Bus
    1.78
     bus
    1.73
    Bus
    1.63
     buses
    1.61
    bus
    1.59
     BUS
    1.54
     Buses
    1.48
     Busse
    1.47
    BUS
    1.41
    buses
    1.29
    Activations Density 0.029%

    No Known Activations