Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12624
    Prev
    Next
    INDEX
    Explanations

    that

    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
     تضيفلها
    -0.61
     conmigo
    -0.57
     istället
    -0.55
    verifyException
    -0.55
     dalamnya
    -0.55
    migrationBuilder
    -0.54
     IBOutlet
    -0.54
    TintMode
    -0.54
     comigo
    -0.53
    argout
    -0.52
    POSITIVE LOGITS
    ########.
    0.77
    ++
    
    0.65
    '));
    
    0.64
     you
    0.63
    \{\\
    0.62
    ']))
    
    0.62
    endphp
    0.60
    '):
    
    0.60
    .";
    
    0.59
    "}\
    0.59
    Activations Density 0.020%

    No Known Activations