© 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. 96631
    Prev
    Next
    INDEX
    Explanations

    Currency/money

    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
    adaptiveStyles
    -0.50
    Naissance
    -0.42
     and
    -0.42
    fony
    -0.41
    prox
    -0.40
    hodné
    -0.40
    észetes
    -0.40
    GRAPHY
    -0.39
    withstanding
    -0.39
    الا
    -0.38
    POSITIVE LOGITS
    multer
    0.70
    AsUp
    0.67
    原始内容存档于
    0.67
     שוליים
    0.66
    /*
    0.62
    Jeografia
    0.61
     annuelle
    0.61
    CodedInputStream
    0.60
    adget
    0.59
     chấm
    0.58
    Activations Density 0.003%

    No Known Activations