© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5452
    Prev
    Next
    INDEX
    Explanations

    percent

    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
    tagHelperRunner
    -0.75
     nahilalakip
    -0.71
     to
    -0.69
    InputBorder
    -0.68
    marle
    -0.58
    while
    -0.58
    to
    -0.56
    intéress
    -0.55
    with
    -0.54
    TagHelper
    -0.54
    POSITIVE LOGITS
     of
    0.71
    AddTagHelper
    0.68
     purity
    0.60
    HtmlAttribute
    0.54
     reliability
    0.54
     accuracy
    0.54
    umna
    0.50
     portability
    0.49
     wholes
    0.49
     Pfeiffer
    0.49
    Activations Density 0.001%

    No Known Activations