© 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. 20-CLT-HP
    7. 76339
    Prev
    Next
    INDEX
    Explanations

    ar

    np_max-act-logits · 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
    __':
    -0.79
    IUrlHelper
    -0.75
    __":
    -0.75
    queryInterface
    -0.71
     <=",
    -0.69
    SharedDtor
    -0.68
    __":
    -0.68
    LabelTagHelper
    -0.68
    __':
    -0.67
    hilation
    -0.67
    POSITIVE LOGITS
    脚注の使い方
    0.55
    lo
    0.47
    tief
    0.45
    kannya
    0.44
    ks
    0.42
    neſs
    0.41
    Component
    0.40
     ks
    0.40
    garh
    0.39
    PRS
    0.39
    Activations Density 0.003%

    No Known Activations