© 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. 1-CLT-HP
    7. 13371
    Prev
    Next
    INDEX
    Explanations

    health

    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
    étro
    -0.56
    enumi
    -0.56
    enumii
    -0.47
    WebElementEntity
    -0.46
    ternal
    -0.46
    ichia
    -0.45
     allé
    -0.44
    ValueGeneration
    -0.43
     hjäl
    -0.43
    éns
    -0.43
    POSITIVE LOGITS
    ंदीखरीदारी
    0.66
     Schlegel
    0.65
    +:+
    0.64
    بوابة
    0.62
    esModule
    0.61
     filmi
    0.59
    )_/¯
    0.59
    yntaxException
    0.57
    __':
    0.57
     Wikimedijinoj
    0.56
    Activations Density 0.135%

    No Known Activations