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. 5-CLT-HP
    4. 95473
    Prev
    Next
    INDEX
    Explanations

    Adding details

    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
    ++
    
    -0.87
     ]
    
    -0.85
    ")]
    
    -0.83
    )";
    
    -0.82
     HasFactory
    -0.81
    '],
    
    -0.81
    MessageOf
    -0.80
    SourceChecksum
    -0.79
    principalColumn
    -0.79
     transférez
    -0.77
    POSITIVE LOGITS
    !
    0.73
    .
    0.62
    ?
    0.57
     tarko
    0.53
     aikana
    0.52
    ;
    0.50
     recommandons
    0.50
     määrä
    0.49
     mahdol
    0.49
     !
    0.48
    Activations Density 0.001%

    No Known Activations