© 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. 77311
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    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
    AndEndTag
    -0.85
    contentLoaded
    -0.84
    yntaxException
    -0.83
    ValueStyle
    -0.77
    detectChanges
    -0.77
    InputBorder
    -0.72
     CreateTagHelper
    -0.71
     AssemblyCulture
    -0.71
     GoogleFonts
    -0.71
    aarrggbb
    -0.69
    POSITIVE LOGITS
     drop
    0.38
     Thi
    0.38
     Penh
    0.38
     diri
    0.37
    gucigalpa
    0.36
    ybė
    0.35
    ွ
    0.35
     Drop
    0.35
     Former
    0.35
    heran
    0.35
    Activations Density 0.000%

    No Known Activations