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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92736
    Prev
    Next
    INDEX
    Explanations

    legal documents/code

    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
    DockStyle
    -0.63
    quelize
    -0.57
    aarrggbb
    -0.57
    تفصیلات
    -0.56
     qu
    -0.55
    ?,?,
    -0.54
    atista
    -0.52
     nahilalakip
    -0.52
    RegistryLite
    -0.51
    ]")]
    -0.49
    POSITIVE LOGITS
     prisms
    0.67
    зулта
    0.63
     Apprentices
    0.60
     yawn
    0.58
    Pty
    0.57
     déchir
    0.57
     concernés
    0.56
     adiós
    0.56
     Ceará
    0.55
     smoo
    0.54
    Activations Density 0.266%

    No Known Activations