© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16130
    Prev
    Next
    INDEX
    Explanations

    magnetic

    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
     للمعارف
    -0.96
    principalColumn
    -0.90
    adeloupe
    -0.88
     betweenstory
    -0.87
    WebVitals
    -0.87
     مرئيه
    -0.86
     صوتيه
    -0.82
     StatefulWidget
    -0.81
     EconPapers
    -0.80
     étoit
    -0.77
    POSITIVE LOGITS
     har
    0.42
     char
    0.42
    to
    0.40
    l
    0.40
    char
    0.39
    on
    0.38
    -
    0.38
     ra
    0.35
    ierre
    0.35
    ry
    0.35
    Activations Density 0.104%

    No Known Activations