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. 0-CLT-HP
    4. 91674
    Prev
    Next
    INDEX
    Explanations

    Source documents/excerpts

    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
    
    -0.64
    anneer
    -0.57
     تانيه
    -0.56
    γέν
    -0.55
    sidemargin
    -0.55
    æde
    -0.52
    abestanden
    -0.52
    +#+#
    -0.50
     élector
    -0.49
    resher
    -0.49
    POSITIVE LOGITS
    ")));
    
    0.59
    "),
    
    0.55
    ุ่น
    0.54
    disposing
    0.52
    ContentAsync
    0.52
    mapStateToProps
    0.51
    <bos>
    0.51
     jaki
    0.51
     zato
    0.51
     doméstica
    0.51
    Activations Density 1.422%

    No Known Activations