© 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. 90944
    Prev
    Next
    INDEX
    Explanations

    professional roles/organizations

    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
     correctional
    -0.50
     conservatory
    -0.50
     acquaintance
    -0.49
     surgery
    -0.48
     venture
    -0.47
     center
    -0.46
     deluxe
    -0.46
     enterprise
    -0.46
     luxury
    -0.46
     dental
    -0.45
    POSITIVE LOGITS
     saites
    0.78
    enumi
    0.75
     للمعارف
    0.69
     antaranya
    0.69
     AssemblyTitle
    0.68
    @[+][
    0.68
    脚注の使い方
    0.66
    Tikang
    0.66
    MLLoader
    0.66
    MessageOf
    0.62
    Activations Density 0.002%

    No Known Activations