© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91577
    Prev
    Next
    INDEX
    Explanations

    delighted

    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
     itſelf
    -0.77
     pleaſure
    -0.74
     AssemblyCulture
    -0.71
    SourceChecksum
    -0.70
    IUrlHelper
    -0.70
     myſelf
    -0.69
    ########.
    -0.67
    Geplaatst
    -0.66
     raiſ
    -0.64
     Majefty
    -0.64
    POSITIVE LOGITS
     "
    0.90
     “
    0.70
     «
    0.67
     '
    0.62
     `
    0.60
     int
    0.58
     „
    0.57
     {
    0.55
    ".
    0.55
     ‘‘
    0.54
    Activations Density 0.009%

    No Known Activations