© 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. 16035
    Prev
    Next
    INDEX
    Explanations

    review

    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
     dipendenti
    -0.64
     próprias
    -0.63
     reviewing
    -0.59
     originais
    -0.58
     spéciaux
    -0.58
     roulant
    -0.58
     GenerationType
    -0.57
    review
    -0.56
     Reviewing
    -0.56
     reviewed
    -0.56
    POSITIVE LOGITS
    EDEFAULT
    0.65
     تضيفلها
    0.63
    ]--;
    0.58
    InteropServices
    0.52
    omitempty
    0.52
     cjs
    0.51
    protoimpl
    0.51
    esModule
    0.50
     contempla
    0.50
     MERCHANTABILITY
    0.49
    Activations Density 0.012%

    No Known Activations