© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    clarification/definition

    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
     getroffen
    -0.50
     exécu
    -0.47
     ruinas
    -0.47
     fausse
    -0.46
     élevées
    -0.46
     atteinte
    -0.45
     pomen
    -0.45
     colina
    -0.44
     falsas
    -0.44
     blessés
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.88
    WebVitals
    0.83
     للمعارف
    0.72
    NewUrlParser
    0.72
    sizeCache
    0.71
    出版年
    0.71
    bootstrapcdn
    0.71
    Obrázky
    0.68
    queryInterface
    0.68
    Portály
    0.67
    Activations Density 0.023%

    No Known Activations