© 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. 75327
    Prev
    Next
    INDEX
    Explanations

    Code and legal snippets

    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
    hasMoreElements
    -0.70
     AssemblyVersion
    -0.68
     Paglinawan
    -0.66
    enumi
    -0.65
    UnusedPrivate
    -0.64
    UseVisualStyle
    -0.63
    Fv
    -0.57
     UIApplication
    -0.57
    AccessorTable
    -0.56
     LEYENDO
    -0.56
    POSITIVE LOGITS
    AddTagHelper
    0.61
     came
    0.60
     come
    0.60
     Come
    0.56
     bpy
    0.55
    TagHelper
    0.54
    uncu
    0.52
    come
    0.51
    Launch
    0.51
     impro
    0.50
    Activations Density 0.000%

    No Known Activations