© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5646
    Prev
    Next
    INDEX
    Explanations

    [

    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
     Normdatei
    -0.51
     división
    -0.46
    split
    -0.46
     ujednoznacz
    -0.44
    ského
    -0.43
     lobo
    -0.43
    copo
    -0.41
     HasFactory
    -0.41
     Us
    -0.41
     for
    -0.41
    POSITIVE LOGITS
    SpringRunner
    0.66
    Спољашње
    0.65
     [*]
    0.64
    fromnode
    0.62
    <!--[
    0.60
    migrationBuilder
    0.59
    ThemeOverlay
    0.58
    ImageContext
    0.57
    <!--
    0.57
    endcsname
    0.56
    Activations Density 0.002%

    No Known Activations