© 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. 0-CLT-HP
    7. 95531
    Prev
    Next
    INDEX
    Explanations

    nutrients

    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
     actually
    -0.80
     ACTUALLY
    -0.73
    actually
    -0.72
    nut
    -0.71
    Actually
    -0.71
     Actually
    -0.71
     faktisk
    -0.66
    ness
    -0.64
    nuts
    -0.64
    NOPQRST
    -0.63
    POSITIVE LOGITS
    TintMode
    0.74
     تضيفلها
    0.71
    tagHelperRunner
    0.70
    DockStyle
    0.69
    bootstrapcdn
    0.66
    LookAnd
    0.65
    AddHtmlAttribute
    0.64
    SourceChecksum
    0.63
    awtextra
    0.62
     defaultstate
    0.61
    Activations Density 1.315%

    No Known Activations