© 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. 5-CLT-HP
    4. 169
    Prev
    Next
    INDEX
    Explanations

    real

    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
    -0.61
     <=",
    -0.59
    NUMX
    -0.56
     NavController
    -0.53
     okuyayım
    -0.53
    itorious
    -0.52
    الدراسه
    -0.52
     Baillargeon
    -0.52
    OrNil
    -0.52
    SequentialGroup
    -0.51
    POSITIVE LOGITS
    world
    0.74
     world
    0.68
     Real
    0.60
    World
    0.59
    real
    0.59
     World
    0.58
    life
    0.56
    WORLD
    0.56
    tact
    0.56
    Real
    0.56
    Activations Density 0.001%

    No Known Activations