© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14232
    Prev
    Next
    INDEX
    Explanations

    references to parking facilities or related infrastructure

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yard
    -0.73
     Yard
    -0.67
    yard
    -0.67
    Yard
    -0.64
    YARD
    -0.62
     Wikimedijinoj
    -0.60
     grass
    -0.59
     césped
    -0.57
     quoting
    -0.56
     yards
    -0.56
    POSITIVE LOGITS
     parking
    2.73
     Parking
    2.42
    Parking
    2.39
     PARKING
    2.20
    parking
    2.11
     estacionamiento
    1.52
     estacionamento
    1.46
     aparcamiento
    1.31
     parcheggio
    1.25
     stationnement
    1.23
    Activations Density 0.001%

    No Known Activations