© 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. 5-CLT-HP
    7. 4922
    Prev
    Next
    INDEX
    Explanations

    dated

    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
     initComponents
    -0.84
    WebElementEntity
    -0.79
     HasFactory
    -0.79
    IntoConstraints
    -0.73
     nakalista
    -0.72
    RegressionTest
    -0.70
     MainAxisSize
    -0.70
    endphp
    -0.69
    WebServlet
    -0.68
    \{\\
    -0.68
    POSITIVE LOGITS
    modelBuilder
    0.46
     radio
    0.42
     +/-
    0.41
     bak
    0.41
    ±
    0.40
     using
    0.40
     to
    0.40
     up
    0.39
    bach
    0.39
    UseVisualStyle
    0.38
    Activations Density 0.000%

    No Known Activations