© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1159
    Prev
    Next
    INDEX
    Explanations

    concluding statements

    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
     démocr
    -0.54
    enterOuterAlt
    -0.52
     revêtement
    -0.50
    ногие
    -0.49
     later
    -0.48
     a
    -0.46
    many
    -0.46
    later
    -0.45
     dommages
    -0.45
    lakukan
    -0.44
    POSITIVE LOGITS
    <bos>
    1.01
     itſelf
    0.95
     myſelf
    0.87
    '},
    
    0.82
     Monfieur
    0.81
    ')));
    0.79
    "]);
    
    0.79
    ]));
    
    0.78
    '):
    
    0.77
    '))
    
    0.76
    Activations Density 0.084%

    No Known Activations