© 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. 5-CLT-HP
    7. 90975
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     africana
    -0.48
     pinulongan
    -0.46
     precede
    -0.46
     exaggerate
    -0.45
    due
    -0.44
     abrigo
    -0.44
     ajuta
    -0.44
    喔
    -0.44
     Egipto
    -0.44
     contral
    -0.44
    POSITIVE LOGITS
     виправивши
    0.82
    windowFixed
    0.66
     ExecuteAsync
    0.66
    posedge
    0.65
    ArgsConstructor
    0.63
    LabelTagHelper
    0.60
    viewDidLoad
    0.60
    tonode
    0.60
    maketitle
    0.60
    umented
    0.60
    Activations Density 0.021%

    No Known Activations