© 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. 20-CLT-HP
    7. 75828
    Prev
    Next
    INDEX
    Explanations

    technical text (best guess)

    np_max-act-logits · 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
     estekak
    -0.67
     NSCoder
    -0.66
    Geplaatst
    -0.65
     himo
    -0.57
    InputTagHelper
    -0.52
    aarrggbb
    -0.51
    цездатний
    -0.50
     defaultstate
    -0.49
     AssemblyCompany
    -0.48
    Javadoc
    -0.48
    POSITIVE LOGITS
    bcryptjs
    0.50
    рованных
    0.49
     Oph
    0.49
     platy
    0.47
     Fru
    0.47
    getR
    0.46
    addKeyListener
    0.45
     Evo
    0.45
     päiv
    0.45
    ranslated
    0.44
    Activations Density 0.004%

    No Known Activations