© 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. 91196
    Prev
    Next
    INDEX
    Explanations

    code fragments

    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
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.97
     BoxDecoration
    -0.90
     disambiguazione
    -0.77
    WithIOException
    -0.76
    SpringBootTest
    -0.74
    .*")]
    -0.71
    Hochspringen
    -0.69
     فريبيس
    -0.67
    )";
    -0.67
     للمعارف
    -0.65
    POSITIVE LOGITS
    ins
    0.49
     hård
    0.46
    idae
    0.45
    unid
    0.44
     puol
    0.42
     hår
    0.41
    inds
    0.41
    Réponse
    0.41
     stål
    0.41
     برانيه
    0.40
    Activations Density 0.003%

    No Known Activations