© 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. 20-CLT-HP
    7. 76618
    Prev
    Next
    INDEX
    Explanations

    code and linguistics

    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
     @"/
    -0.68
    ètement
    -0.57
    verwijspagina
    -0.57
    ंदीखरीदारी
    -0.56
    homonymie
    -0.52
    InjectAttribute
    -0.52
    Véxase
    -0.52
    +#+#
    -0.50
     AssemblyCulture
    -0.49
     الحره
    -0.48
    POSITIVE LOGITS
     place
    0.56
    Dur
    0.52
     CreateTagHelper
    0.52
     Place
    0.50
    ционное
    0.50
    BagLayout
    0.49
    place
    0.49
    writeField
    0.49
     PLACE
    0.48
    eció
    0.48
    Activations Density 0.000%

    No Known Activations