© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8862
    Prev
    Next
    INDEX
    Explanations

    operating systems

    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
    Negative Logits
    ing
    -0.52
     sun
    -0.51
    cu
    -0.47
    abit
    -0.46
    aca
    -0.45
     ho
    -0.44
    broek
    -0.43
    vall
    -0.43
    anak
    -0.43
     cour
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.96
     bezeichneter
    0.89
    انجليز
    0.85
     protoimpl
    0.85
    setVerticalGroup
    0.85
     يتيمه
    0.85
     OFDb
    0.84
    DockStyle
    0.83
    -------------</
    0.82
     autorytatywna
    0.80
    Activations Density 0.033%

    No Known Activations