© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2322
    Prev
    Next
    INDEX
    Explanations

    family

    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
    تقاوى
    -0.59
    writeField
    -0.52
    sizeCache
    -0.48
    abestanden
    -0.47
    LookAnd
    -0.47
    EndInit
    -0.47
    ėjimo
    -0.46
     épo
    -0.46
     Applied
    -0.46
    ToTable
    -0.46
    POSITIVE LOGITS
    ChildScrollView
    0.83
     AppColors
    0.66
    setVerticalGroup
    0.62
    BeginContext
    0.60
    createCanvas
    0.59
     firebaseConfig
    0.59
     跳转至
    0.59
     InputDecoration
    0.58
    LabelTagHelper
    0.57
    czegó
    0.56
    Activations Density 0.147%

    No Known Activations