© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77618
    Prev
    Next
    INDEX
    Explanations

    Technical documentation snippets

    np_max-act-logits · 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
     يتيمه
    -0.73
    awtextra
    -0.65
     Administrativna
    -0.63
    OGND
    -0.62
    +#+#
    -0.61
    mybatisplus
    -0.60
     InputDecoration
    -0.57
     GetEnumerator
    -0.56
    NewUrlParser
    -0.56
    Personensuche
    -0.55
    POSITIVE LOGITS
    TOP
    0.56
    Попис
    0.50
    ronique
    0.47
    DetailActivity
    0.43
    olda
    0.43
     rubbed
    0.43
    tek
    0.42
    ارش
    0.41
    ABBA
    0.41
     ger
    0.41
    Activations Density 0.008%

    No Known Activations