© 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. 8697
    Prev
    Next
    INDEX
    Explanations

    gram

    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
     marine
    -0.50
     of
    -0.44
    <bos>
    -0.42
     flot
    -0.42
    Marine
    -0.40
    fluss
    -0.40
    '
    -0.40
    ↵↵
    -0.40
    cientos
    -0.40
    ’
    -0.40
    POSITIVE LOGITS
    SharedDtor
    1.07
    contentLoaded
    1.02
     ComVisible
    1.02
     MainAxisSize
    1.02
    TypedDataSet
    0.98
    AddTagHelper
    0.92
     المعيارى
    0.92
    ftagPool
    0.89
     Roskov
    0.88
     ویکی‌پدیا
    0.88
    Activations Density 0.050%

    No Known Activations