© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5675
    Prev
    Next
    INDEX
    Explanations

    transform

    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
    ıştır
    -0.47
     TextInputType
    -0.47
    potranspiration
    -0.44
    ólica
    -0.44
     ComVisible
    -0.43
    withstanding
    -0.42
     оригіналу
    -0.42
    extAlignment
    -0.42
    andaag
    -0.41
     FIRM
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.98
    MemoryWarning
    0.82
     from
    0.69
    MigrationBuilder
    0.66
     تضيفلها
    0.66
    SuspendLayout
    0.60
    homonymie
    0.60
    sizeCache
    0.60
     الرياضيه
    0.59
    webElementXpaths
    0.58
    Activations Density 0.001%

    No Known Activations