© 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. 71908
    Prev
    Next
    INDEX
    Explanations

    flat surfaces

    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
     télécommande
    -0.56
     Phases
    -0.55
     eventdata
    -0.54
     "..\..\..\
    -0.52
    rhosis
    -0.51
    PreAuthorize
    -0.51
    出版年
    -0.51
     kasarigan
    -0.50
     apellidos
    -0.50
    UserScript
    -0.50
    POSITIVE LOGITS
     board
    0.81
     plate
    0.62
     lamina
    0.61
     surface
    0.60
     table
    0.60
     support
    0.58
     strip
    0.57
     disk
    0.57
     level
    0.56
     disc
    0.55
    Activations Density 0.002%

    No Known Activations