© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74825
    Prev
    Next
    INDEX
    Explanations

    Technical text

    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
    :✨
    -0.82
    PreferredItem
    -0.73
    AddHtmlAttribute
    -0.70
     ISNI
    -0.62
     relâche
    -0.58
     typelib
    -0.58
    MigrationBuilder
    -0.56
    twimg
    -0.53
    nanoTime
    -0.52
    脚注の使い方
    -0.52
    POSITIVE LOGITS
     restricted
    0.60
     Restricted
    0.58
     Hill
    0.52
     ELEMENTS
    0.52
    RepeatedField
    0.51
     integrals
    0.50
    цездатний
    0.49
     HILL
    0.49
    restricted
    0.48
     elements
    0.47
    Activations Density 0.000%

    No Known Activations