© 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. 1-CLT-HP
    7. 10516
    Prev
    Next
    INDEX
    Explanations

    E

    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
    TagMode
    -0.71
    AddTagHelper
    -0.66
     للمعارف
    -0.65
    MessageOf
    -0.62
    <bos>
    -0.59
     وتسجيلات
    -0.57
     محفوظة
    -0.56
    ReusableCell
    -0.56
    JNIEnv
    -0.54
     ympä
    -0.52
    POSITIVE LOGITS
    fic
    0.59
    Pre
    0.56
    IConfiguration
    0.53
    ználat
    0.52
    FIC
    0.52
     pre
    0.52
    ########.
    0.51
     Preg
    0.51
    QUIS
    0.51
    pre
    0.51
    Activations Density 0.056%

    No Known Activations