Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12597
    Prev
    Next
    INDEX
    Explanations

    Technical specifications/types

    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
    aurus
    -0.51
    ly
    -0.49
    s
    -0.48
    ات
    -0.47
    amis
    -0.46
    ote
    -0.46
    了
    -0.44
     Gar
    -0.42
    ую
    -0.42
    au
    -0.42
    POSITIVE LOGITS
    AccessorTable
    0.88
    JspWriter
    0.85
    AddTagHelper
    0.84
     AssemblyProduct
    0.80
     jScrollPane
    0.79
    makeConstraints
    0.76
     myſelf
    0.76
     oprot
    0.74
    MessageTagHelper
    0.74
    brities
    0.74
    Activations Density 0.003%

    No Known Activations