© 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. 0-CLT-HP
    7. 97442
    Prev
    Next
    INDEX
    Explanations

    belle

    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
     CreateTagHelper
    -0.92
     estimés
    -0.77
    Xna
    -0.76
     Equation
    -0.70
    alleros
    -0.67
     StatelessWidget
    -0.67
     equation
    -0.65
    Equation
    -0.65
    providedIn
    -0.65
    ives
    -0.63
    POSITIVE LOGITS
    <bos>
    0.70
    v
    0.45
     noastre
    0.45
    מ
    0.44
     BoxFit
    0.43
    m
    0.43
    g
    0.43
    ponses
    0.42
     shares
    0.42
     fortnight
    0.42
    Activations Density 0.256%

    No Known Activations