© 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. 4-CLT-HP
    7. 1708
    Prev
    Next
    INDEX
    Explanations

    faith

    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
     autorytatywna
    -0.79
    ंदीखरीदारी
    -0.65
    IntoConstraints
    -0.64
    Autoritní
    -0.64
    Manbalar
    -0.62
    IGraphics
    -0.59
    mappedBy
    -0.58
    %)$
    -0.57
    قایناقلار
    -0.57
    IMPORTED
    -0.57
    POSITIVE LOGITS
    fulness
    0.50
    ful
    0.46
    urig
    0.45
    bruck
    0.43
    FormTagHelper
    0.43
    yaç
    0.41
    letics
    0.41
    UnitTesting
    0.41
    bright
    0.40
    HasAnnotation
    0.39
    Activations Density 0.010%

    No Known Activations