© 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. 4-CLT-HP
    4. 4973
    Prev
    Next
    INDEX
    Explanations

    Code and articles

    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
    LEncoder
    -0.63
     <>",
    -0.51
    Viited
    -0.49
    ']))
    
    -0.49
    }.
    
    -0.48
    >>;
    -0.48
    sees
    -0.48
    '])
    
    -0.47
     Klasse
    -0.47
    ...");
    
    -0.47
    POSITIVE LOGITS
    EndContext
    0.59
    MigrationBuilder
    0.55
    ciutto
    0.54
     تضيفلها
    0.53
    resizingMask
    0.53
    handlebars
    0.52
     صوتيه
    0.52
    AccessFile
    0.50
     وتسجيلات
    0.50
     intptr
    0.50
    Activations Density 0.019%

    No Known Activations