© 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. 0-CLT-HP
    4. 38549
    Prev
    Next
    INDEX
    Explanations

    World War or half

    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
    oa̍t
    -0.77
     NSCoder
    -0.77
    ագրություններ
    -0.74
     lenker
    -0.70
    setVerticalGroup
    -0.67
    bcryptjs
    -0.66
     mouthful
    -0.65
    reportWebVitals
    -0.65
     AssemblyCompany
    -0.64
     متعلقه
    -0.63
    POSITIVE LOGITS
     rés
    0.47
     the
    0.45
    punkte
    0.44
    }{#
    0.44
    enskap
    0.42
    utum
    0.40
     cebo
    0.40
    case
    0.40
    ital
    0.39
    gway
    0.39
    Activations Density 0.020%

    No Known Activations