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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 41395
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    AL
    -0.72
    use
    -0.65
    참고
    -0.65
    idase
    -0.57
    tiva
    -0.54
    JEL
    -0.52
    Demografia
    -0.52
    fixed
    -0.52
    I
    -0.51
    原始内容存档于
    -0.49
    POSITIVE LOGITS
    -
    
    0.69
    )");
    
    0.68
    }")
    
    0.65
     photolibrary
    0.64
    ++
    
    0.63
     विश्वसनीयता
    0.59
     >=",
    0.59
     ';
    
    0.59
     οποίο
    0.58
     FetchType
    0.57
    Activations Density 0.697%

    No Known Activations