© 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. 76781
    Prev
    Next
    INDEX
    Explanations

    coding/programming

    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
     CreateTagHelper
    -0.63
     defaultstate
    -0.59
    initComponents
    -0.54
     stabilité
    -0.53
    principalColumn
    -0.52
    __':
    -0.50
     entregado
    -0.49
    isNullOrEmpty
    -0.49
     tocado
    -0.49
    ագրություններ
    -0.48
    POSITIVE LOGITS
     a
    0.60
    BeginContext
    0.57
    PreferredItem
    0.52
    vair
    0.52
    пать
    0.50
     
    0.47
    utex
    0.47
     referenties
    0.47
     colours
    0.46
     Error
    0.46
    Activations Density 0.000%

    No Known Activations