© 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. 2800
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
    UTUP
    -0.59
    gotten
    -0.57
    ALTH
    -0.55
     الرياضيه
    -0.55
     ویکی‌پدی
    -0.54
    ויות
    -0.52
    uiente
    -0.51
    OfThe
    -0.49
    |()
    -0.49
    OGND
    -0.49
    POSITIVE LOGITS
     whoſe
    0.72
    TagMode
    0.69
    JspWriter
    0.63
    Personensuche
    0.61
    LabelTagHelper
    0.60
     puissiez
    0.57
     setuptools
    0.57
     becauſe
    0.57
     rospy
    0.56
     tempio
    0.56
    Activations Density 0.004%

    No Known Activations