© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92577
    Prev
    Next
    INDEX
    Explanations

    license agreement/URL webtext

    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
    ↵
    -0.49
    getMinutes
    -0.45
    łys
    -0.44
    ↵↵
    -0.42
     costing
    -0.41
     all
    -0.40
     his
    -0.40
     Komisi
    -0.40
    jaardag
    -0.40
    s
    -0.40
    POSITIVE LOGITS
     الرياضيه
    0.92
    abestanden
    0.91
     protoimpl
    0.86
    principalTable
    0.77
     متعلقه
    0.77
    ValueStyle
    0.76
    )");
    
    0.75
    rungsseite
    0.73
    حوالہ
    0.73
    UARY
    0.72
    Activations Density 0.154%

    No Known Activations