© 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. 20-CLT-HP
    7. 76499
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    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
     lenker
    -0.53
    ByExample
    -0.51
    lapsingToolbar
    -0.50
    IUrlHelper
    -0.49
    lismo
    -0.48
    hető
    -0.47
    заи
    -0.47
    ogaster
    -0.47
     coales
    -0.45
    inspace
    -0.45
    POSITIVE LOGITS
     propOrder
    0.87
    Rujuakan
    0.60
    Билгалдахарш
    0.57
    YAN
    0.52
    resizingMask
    0.50
    HomeAsUpEnabled
    0.50
    WebControls
    0.50
    nodoc
    0.49
    XMLSchema
    0.49
    frontmatter
    0.49
    Activations Density 0.006%

    No Known Activations