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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12266
    Prev
    Next
    INDEX
    Explanations

    negative

    np_max-act · 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
    DockStyle
    -0.77
    :✨
    -0.60
    ModelAdmin
    -0.58
    LayoutStyle
    -0.56
    inian
    -0.53
    heira
    -0.52
     للاسماء
    -0.52
    richTextPanel
    -0.51
    TestFixture
    -0.51
    PerformLayout
    -0.49
    POSITIVE LOGITS
    Xna
    0.67
    lucene
    0.60
     viewDid
    0.57
     smtplib
    0.56
     trovar
    0.53
    atchi
    0.51
    enchymal
    0.51
     cavo
    0.50
    allclose
    0.50
     llevo
    0.50
    Activations Density 0.048%

    No Known Activations