© 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. 71921
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     initComponents
    -0.86
    webElement
    -0.69
     useAppContext
    -0.56
    PreferredItem
    -0.56
     CreateTagHelper
    -0.54
    ThroughAttribute
    -0.53
    SPATH
    -0.52
     Constantin
    -0.50
    httphttps
    -0.50
    WebVitals
    -0.50
    POSITIVE LOGITS
     preload
    0.54
    最快更新
    0.47
     dissi
    0.46
    GeneratedValue
    0.45
    oniec
    0.45
    PhysRevD
    0.45
     delan
    0.45
    Zunanje
    0.42
     quilts
    0.42
     Marrow
    0.41
    Activations Density 0.002%

    No Known Activations