© 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. 40326
    Prev
    Next
    INDEX
    Explanations

    disrupting

    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
    httphttps
    -0.84
    IUrlHelper
    -0.82
    脚注の使い方
    -0.80
     Audiodateien
    -0.78
     collation
    -0.78
     disrupting
    -0.78
     electing
    -0.76
    #+#
    -0.75
     otomatig
    -0.75
    transQ
    -0.74
    POSITIVE LOGITS
    omys
    0.51
     to
    0.45
    ^{\
    0.44
    خد
    0.43
    endrait
    0.43
     Administração
    0.40
     (
    0.40
    役
    0.39
    tos
    0.39
    рам
    0.38
    Activations Density 1.647%

    No Known Activations