© 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. 96847
    Prev
    Next
    INDEX
    Explanations

    Levels and positions

    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
    stretchr
    -0.48
     Earth
    -0.47
    íté
    -0.47
     pozosta
    -0.47
    downcase
    -0.47
    __':
    -0.46
    stay
    -0.45
     bleiben
    -0.45
    Earth
    -0.45
     down
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.79
    MessageTagHelper
    0.75
     referenties
    0.75
    contentLoaded
    0.69
    Diwedd
    0.63
     समीक्षाओं
    0.63
     виправивши
    0.60
     Roskov
    0.59
     Référence
    0.58
    出版年
    0.58
    Activations Density 0.002%

    No Known Activations