© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    import

    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
    EndProject
    -0.87
     utafitiHapana
    -0.75
    Personensuche
    -0.74
     himo
    -0.66
    webElementXpaths
    -0.65
    Tembelea
    -0.61
    Externí
    -0.60
    AddTagHelper
    -0.60
    apimachinery
    -0.60
     téléchargez
    -0.59
    POSITIVE LOGITS
     describing
    0.43
    like
    0.43
     Majefty
    0.42
    LIKE
    0.40
     settling
    0.40
     harmless
    0.40
     Aún
    0.40
     dope
    0.39
     abnormally
    0.39
    んだろう
    0.39
    Activations Density 0.010%

    No Known Activations