© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40543
    Prev
    Next
    INDEX
    Explanations

    user identification

    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
    personal
    -1.23
    Personal
    -1.04
    PERSONAL
    -0.89
     personnelle
    -0.88
     PERSONAL
    -0.84
    user
    -0.82
     Personal
    -0.82
    User
    -0.81
    ersonal
    -0.81
     personale
    -0.79
    POSITIVE LOGITS
     cherchés
    0.75
    addPreferredGap
    0.71
     חיצוניים
    0.66
    Искәрмәләр
    0.64
    \{\\
    0.63
    LayoutConstraint
    0.61
    getWriter
    0.61
    brainly
    0.60
    Билгалдахарш
    0.59
     <<<<<<<<<<<<<<
    0.58
    Activations Density 1.564%

    No Known Activations