© 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. 1-CLT-HP
    4. 897
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    <bos>
    -0.64
    nonatomic
    -0.56
    otient
    -0.54
    openzeppelin
    -0.53
    DockStyle
    -0.49
     Sociological
    -0.49
     Olivier
    -0.47
     lied
    -0.46
    apikey
    -0.46
    uxxxx
    -0.46
    POSITIVE LOGITS
    '}>
    0.61
    >");
    
    0.57
    espoir
    0.57
    )");
    
    0.56
    "]);
    
    0.53
     pertes
    0.52
    ())));
    0.50
    تقاوى
    0.50
     enfans
    0.49
    hogs
    0.49
    Activations Density 0.080%

    No Known Activations