© 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. 16108
    Prev
    Next
    INDEX
    Explanations

    economic analysis/research

    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
    BeginContext
    -0.87
    <bos>
    -0.86
    تقاوى
    -0.72
     CreateTagHelper
    -0.72
    ScopeManager
    -0.69
    ModelSerializer
    -0.68
    DataAnnotations
    -0.66
     LUMP
    -0.66
    mybatisplus
    -0.64
    ParallelGroup
    -0.62
    POSITIVE LOGITS
    trique
    0.47
    Rr
    0.46
    fromnode
    0.45
    correspond
    0.44
    teros
    0.43
    tagHelperRunner
    0.43
    strar
    0.43
     recto
    0.43
    biam
    0.43
    ungalows
    0.42
    Activations Density 0.007%

    No Known Activations