© 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. 4-CLT-HP
    7. 2400
    Prev
    Next
    INDEX
    Explanations

    Defining/naming something

    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
    AddTagHelper
    -0.68
    Demografie
    -0.57
    <bos>
    -0.55
    Geplaatst
    -0.54
    تقاوى
    -0.54
    kháu
    -0.54
    #
    -0.51
    AddHtmlAttribute
    -0.50
    ніципа
    -0.48
     StatelessWidget
    -0.48
    POSITIVE LOGITS
     dieux
    0.63
    NUMX
    0.58
     eût
    0.57
    혔
    0.56
     SQLException
    0.56
     Grecs
    0.55
    ContentLoaded
    0.55
     enfans
    0.54
     vervol
    0.54
    Javadoc
    0.53
    Activations Density 0.015%

    No Known Activations