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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45945
    Prev
    Next
    INDEX
    Explanations

    streets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Street
    -1.27
    Street
    -1.10
    street
    -1.02
     STREET
    -1.01
     street
    -0.96
    STREET
    -0.90
     Road
    -0.83
    road
    -0.78
     road
    -0.73
    Road
    -0.69
    POSITIVE LOGITS
    engertian
    0.60
     disponibilités
    0.59
    idjan
    0.50
     الدولى
    0.50
     bezeichneter
    0.49
     CITED
    0.47
     comuniques
    0.47
    atedral
    0.47
    atisfaction
    0.47
    iterranean
    0.47
    Activations Density 0.017%

    No Known Activations