© 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. 1-CLT-HP
    7. 10648
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    cess
    -1.04
    cessed
    -0.76
     Huguen
    -0.62
     Cæsar
    -0.61
     Charlemagne
    -0.60
     Nere
    -0.60
    ccess
    -0.57
    cessor
    -0.57
     tassels
    -0.56
    <bos>
    -0.56
    POSITIVE LOGITS
    databind
    0.59
    PageIndex
    0.54
    laye
    0.50
     okuyayım
    0.49
    íp
    0.48
    ínű
    0.47
    riwal
    0.47
     оригіналу
    0.46
    ReusableCell
    0.46
     рі
    0.46
    Activations Density 0.023%

    No Known Activations