© 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. 5216
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
    that
    -0.61
     quæ
    -0.60
    a
    -0.57
    you
    -0.54
    the
    -0.54
    our
    -0.52
     habet
    -0.51
    where
    -0.51
    this
    -0.50
    your
    -0.49
    POSITIVE LOGITS
     And
    1.02
     and
    0.86
     But
    0.86
     CreateTagHelper
    0.82
     As
    0.79
     (
    0.75
     At
    0.72
     They
    0.71
    setViewportView
    0.69
     By
    0.69
    Activations Density 0.003%

    No Known Activations