© 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. 4-CLT-HP
    7. 4772
    Prev
    Next
    INDEX
    Explanations

    println

    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
    ēs
    -0.40
    最快更新
    -0.39
     JUGA
    -0.39
    খন
    -0.37
    خخ
    -0.37
     KICK
    -0.37
    żar
    -0.36
     Quad
    -0.36
     Karlsruhe
    -0.36
    Źródło
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.79
     Normdatei
    0.78
    DeleteBehavior
    0.73
    Autoritní
    0.71
    MessageTagHelper
    0.71
    Enllaces
    0.70
    VersionUID
    0.69
    Zeneca
    0.69
     configureStore
    0.67
    AutoField
    0.66
    Activations Density 0.015%

    No Known Activations