© 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. 4-CLT-HP
    4. 2864
    Prev
    Next
    INDEX
    Explanations

    in

    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
    eseorang
    -0.70
    transQ
    -0.66
     abbraccio
    -0.64
    ChildScrollView
    -0.56
    aronder
    -0.54
    ineries
    -0.54
    Amicalement
    -0.54
     $_"
    -0.53
     every
    -0.53
     a
    -0.53
    POSITIVE LOGITS
    DockStyle
    0.68
    ISupport
    0.50
     Normdatei
    0.50
    routeProvider
    0.49
     CreateTagHelper
    0.49
    ImageContext
    0.48
    prefixer
    0.48
    Хьажоргаш
    0.47
    MeasureSpec
    0.46
    sendRedirect
    0.46
    Activations Density 0.002%

    No Known Activations