© 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. 1-CLT-HP
    4. 46219
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Denmark
    -0.73
     Norway
    -0.68
     Finland
    -0.63
     Sweden
    -0.60
     Suecia
    -0.59
    Denmark
    -0.58
     sweden
    -0.57
     België
    -0.55
     Dinamarca
    -0.55
     Holland
    -0.54
    POSITIVE LOGITS
     defaultstate
    0.73
    EDEFAULT
    0.71
    ंदीखरीदारी
    0.63
    uronic
    0.62
     Meksiku
    0.60
    DJANGO
    0.59
    SequentialGroup
    0.56
    thâu
    0.54
    WindowConstants
    0.53
    koning
    0.52
    Activations Density 0.028%

    No Known Activations