© 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. 5-CLT-HP
    7. 93578
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
    帖最后由
    -0.53
    ChildScrollView
    -0.46
    setVerticalGroup
    -0.46
    tonode
    -0.45
     For
    -0.45
     welcomed
    -0.45
    حياته
    -0.43
     College
    -0.43
    versite
    -0.43
    WebControls
    -0.43
    POSITIVE LOGITS
    mobileqq
    0.58
     whoſe
    0.57
     autorytatywna
    0.57
    IUrlHelper
    0.56
     purpoſe
    0.55
     تضيفلها
    0.53
     themſelves
    0.52
     neceffary
    0.51
     juſt
    0.51
    +][
    0.50
    Activations Density 0.010%

    No Known Activations