© 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. 97466
    Prev
    Next
    INDEX
    Explanations

    area

    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
     exposure
    -0.91
    exposure
    -0.59
    Exposure
    -0.58
    ValueStyle
    -0.58
     بيها
    -0.57
     exposed
    -0.57
     Exposure
    -0.57
     EXPOSURE
    -0.55
     الاطلاع
    -0.55
    transQ
    -0.52
    POSITIVE LOGITS
     Económica
    0.60
     ujednoznacz
    0.57
    Véxase
    0.57
     doubtnut
    0.57
    quelles
    0.56
    walde
    0.55
    ñadir
    0.54
    ształ
    0.53
    geordneten
    0.52
     Constitucional
    0.52
    Activations Density 0.081%

    No Known Activations