© 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. 72859
    Prev
    Next
    INDEX
    Explanations

    Code, equations, and 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
     receive
    -0.77
    receive
    -0.69
     receives
    -0.68
    Played
    -0.62
     Being
    -0.60
     Receives
    -0.60
     meets
    -0.59
     Played
    -0.59
    provide
    -0.58
     Provides
    -0.58
    POSITIVE LOGITS
     autorytatywna
    0.69
     Roskov
    0.68
    OGND
    0.67
     ModelExpression
    0.66
    principalTable
    0.60
     betweenstory
    0.58
     CreateTagHelper
    0.54
    PerformLayout
    0.54
    iomanip
    0.53
     EClass
    0.51
    Activations Density 0.003%

    No Known Activations