© 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. 5-CLT-HP
    7. 94442
    Prev
    Next
    INDEX
    Explanations

    special

    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
     تضيفلها
    -0.56
    енча
    -0.55
    rawDesc
    -0.53
     JADX
    -0.52
    DockStyle
    -0.52
    ">//
    -0.52
    Personensuche
    -0.50
    SequentialGroup
    -0.50
    SharedCtor
    -0.50
    CppCodeGen
    -0.50
    POSITIVE LOGITS
     in
    0.61
     Within
    0.60
    within
    0.59
     area
    0.58
     EconPapers
    0.57
     field
    0.56
    Within
    0.56
     Amongst
    0.56
     within
    0.56
     WITHIN
    0.56
    Activations Density 0.003%

    No Known Activations