© 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. 20-CLT-HP
    7. 71745
    Prev
    Next
    INDEX
    Explanations

    positive intensifiers

    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
    endphp
    -0.63
    RenderAtEndOf
    -0.58
    Skocz
    -0.55
    getDoctrine
    -0.50
    Configurer
    -0.50
     roth
    -0.50
     nonatomic
    -0.50
    FTFY
    -0.49
    TagHelper
    -0.49
    WidgetItem
    -0.49
    POSITIVE LOGITS
     nicely
    1.25
     fine
    1.13
     beautifully
    1.13
     splendid
    1.13
     wonderfully
    1.02
     excellently
    0.97
     superbly
    0.95
     really
    0.93
    fine
    0.93
     excellent
    0.92
    Activations Density 0.000%

    No Known Activations