© 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. 8952
    Prev
    Next
    INDEX
    Explanations

    training

    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
     насељу
    -0.78
    GEBURTSDATUM
    -0.74
    RenderAtEndOf
    -0.73
    ImageContext
    -0.73
    TypedDataSet
    -0.73
    OGND
    -0.71
    findpost
    -0.71
    Vidite
    -0.70
    TintMode
    -0.67
     ExecuteAsync
    -0.65
    POSITIVE LOGITS
    onBackPressed
    0.51
    Classes
    0.51
    izop
    0.50
    ichia
    0.50
    wachen
    0.50
    duğu
    0.50
    epide
    0.50
     Bonn
    0.49
    Pager
    0.49
     Classes
    0.49
    Activations Density 0.088%

    No Known Activations