© 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. 20-CLT-HP
    7. 73724
    Prev
    Next
    INDEX
    Explanations

    technical / legal language

    np_max-act-logits · 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
     doInBackground
    -0.83
    AddTagHelper
    -0.68
    espère
    -0.67
    UnusedPrivate
    -0.66
    WriteTagHelper
    -0.66
    hyrchwyd
    -0.63
     GreatSchools
    -0.62
    MLLoader
    -0.60
    ICEF
    -0.60
     desglose
    -0.59
    POSITIVE LOGITS
    obox
    0.52
    anno
    0.44
    an
    0.44
    ank
    0.43
     tim
    0.41
    ination
    0.41
    co
    0.41
    fml
    0.41
     lúc
    0.40
     box
    0.39
    Activations Density 0.000%

    No Known Activations