© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92987
    Prev
    Next
    INDEX
    Explanations

    Impaired driving/health measurements

    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
    ंदीखरीदारी
    -0.67
     CreateTagHelper
    -0.66
    SourceChecksum
    -0.65
     uuidv
    -0.64
    utenants
    -0.60
     layui
    -0.57
    signia
    -0.57
    rowser
    -0.57
    tawesome
    -0.56
    digan
    -0.56
    POSITIVE LOGITS
     by
    0.49
    enumi
    0.46
    harusnya
    0.45
    Served
    0.45
    StoreMessageInfo
    0.43
    ;#
    0.42
     Another
    0.41
    SuccessListener
    0.41
     manejo
    0.40
     établi
    0.40
    Activations Density 0.002%

    No Known Activations