© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97068
    Prev
    Next
    INDEX
    Explanations

    statistics/numbers

    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
    seen
    -0.78
    seven
    -0.78
    +#+#
    -0.74
    side
    -0.69
     CreateTagHelper
    -0.68
    OGND
    -0.67
    ⓧ
    -0.65
    URLException
    -0.64
    six
    -0.60
    sever
    -0.60
    POSITIVE LOGITS
    ly
    1.42
    LY
    0.92
    theless
    0.83
    mente
    0.74
    fully
    0.70
    withstanding
    0.68
    wards
    0.66
    tably
    0.66
    neath
    0.65
    ial
    0.65
    Activations Density 0.045%

    No Known Activations