© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 6290
    Prev
    Next
    INDEX
    Explanations

    Numbers and grades

    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
    Negative Logits
    Jereo
    -0.65
     betweenstory
    -0.64
    antung
    -0.60
    )|\
    -0.59
    '):
    
    -0.59
    "):
    
    -0.59
    /");
    -0.58
    ंदीखरीदारी
    -0.57
    '),
    
    -0.57
    '],
    
    -0.57
    POSITIVE LOGITS
    .
    0.70
     שוליים
    0.59
    fjspx
    0.50
     in
    0.48
    SequentialGroup
    0.48
    раздо
    0.48
     wept
    0.47
     respectively
    0.47
     to
    0.47
    Tikang
    0.46
    Activations Density 0.001%

    No Known Activations