© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75606
    Prev
    Next
    INDEX
    Explanations

    direction changes

    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
    ChromeDriver
    -0.67
    styleType
    -0.56
     Rema
    -0.54
    prepareStatement
    -0.53
    AddHtmlAttribute
    -0.52
    topper
    -0.51
    addImage
    -0.50
    #+#
    -0.50
    initializeApp
    -0.50
    glasses
    -0.49
    POSITIVE LOGITS
     turns
    1.29
     turn
    1.23
    turn
    0.99
     turning
    0.96
    Turn
    0.94
    turns
    0.93
     sharp
    0.93
     curve
    0.92
     curves
    0.91
     Turn
    0.90
    Activations Density 0.008%

    No Known Activations