© 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. 91672
    Prev
    Next
    INDEX
    Explanations

    data transfer

    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
     متعلقه
    -0.98
     виправивши
    -0.94
    AddTagHelper
    -0.89
     CreateTagHelper
    -0.84
     <>",
    -0.78
    setVerticalGroup
    -0.77
    AsUp
    -0.77
     CURIAM
    -0.77
     transférez
    -0.74
     autorytatywna
    -0.74
    POSITIVE LOGITS
     to
    1.01
    to
    0.60
     přístup
    0.40
    kket
    0.38
    équi
    0.37
     Auß
    0.36
    äld
    0.36
    Интер
    0.35
    árias
    0.35
     tongue
    0.35
    Activations Density 0.006%

    No Known Activations