© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    ahan

    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
    ahan
    -1.52
    AHAN
    -1.12
    PreferredItem
    -0.71
    الإنجليزية
    -0.68
     Carlos
    -0.67
    __':
    -0.66
    URLException
    -0.65
    haan
    -0.64
    __":
    -0.60
    الحياه
    -0.59
    POSITIVE LOGITS
     AssemblyVersion
    0.53
    queryInterface
    0.52
    lage
    0.48
    im
    0.45
     transférez
    0.45
     opportunity
    0.44
    ing
    0.44
     automatica
    0.43
    ışık
    0.42
    FieldBuilder
    0.42
    Activations Density 0.014%

    No Known Activations