© 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. 0-CLT-HP
    7. 95066
    Prev
    Next
    INDEX
    Explanations

    emission, nm

    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
     EconPapers
    -0.84
     propOrder
    -0.74
     resourceCulture
    -0.70
     ExecuteAsync
    -0.66
    <bos>
    -0.64
    #
    -0.64
     CreateTagHelper
    -0.62
    ⓧ
    -0.58
    aarrggbb
    -0.57
    >{@
    -0.57
    POSITIVE LOGITS
     purpoſe
    0.59
     ſur
    0.58
     Anſ
    0.58
     greateſt
    0.57
     vocale
    0.57
     ſte
    0.56
     ſever
    0.54
     habet
    0.53
     pleaſure
    0.53
    devamını
    0.52
    Activations Density 0.684%

    No Known Activations