© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 761
    Prev
    Next
    INDEX
    Explanations

    The word "to" with hyphens

    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
    发表于
    -0.69
    MessageOf
    -0.65
    SceneManagement
    -0.57
    WebControls
    -0.56
     sureties
    -0.54
    RegressionTest
    -0.54
    gwt
    -0.54
    Signatures
    -0.53
     quoti
    -0.50
    asteroide
    -0.50
    POSITIVE LOGITS
    migrationBuilder
    0.73
     live
    0.62
     feel
    0.60
    सन्दर्भ
    0.58
     yourself
    0.57
     express
    0.57
    didReceive
    0.55
     Walkover
    0.53
     navigate
    0.53
     heal
    0.53
    Activations Density 0.000%

    No Known Activations