© 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. 93329
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Gemeinden
    -0.52
    SHADER
    -0.52
     ellos
    -0.49
     it
    -0.49
     استنادى
    -0.47
     defStyle
    -0.47
    ViewImports
    -0.46
    élica
    -0.46
     őket
    -0.46
    itev
    -0.46
    POSITIVE LOGITS
    ✨:
    0.67
    AndEndTag
    0.67
    клопе
    0.59
    withstanding
    0.57
     Normdatei
    0.54
    %</
    0.54
    IsMutable
    0.53
    TagHelper
    0.52
     scenes
    0.52
    AnchorStyles
    0.52
    Activations Density 0.004%

    No Known Activations