© 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. 5-CLT-HP
    4. 2514
    Prev
    Next
    INDEX
    Explanations

    bring

    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
     CreateTagHelper
    -0.80
     protoimpl
    -0.73
    BagConstraints
    -0.66
    InputBorder
    -0.65
    testify
    -0.64
     فريبيس
    -0.63
    __*/
    -0.62
    Билгалдахарш
    -0.61
    ettür
    -0.61
    PDOException
    -0.59
    POSITIVE LOGITS
    inside
    0.56
     Inside
    0.55
     work
    0.54
     Into
    0.53
     inside
    0.53
     a
    0.52
    Inside
    0.51
    urp
    0.48
     INTO
    0.48
    Into
    0.47
    Activations Density 0.004%

    No Known Activations