© 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. 0-CLT-HP
    7. 95444
    Prev
    Next
    INDEX
    Explanations

    Maxim/dii

    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
     itſelf
    -2.00
     myſelf
    -1.86
     Efq
    -1.85
     ―――――
    -1.76
     Monfieur
    -1.75
     themſelves
    -1.70
     Jefus
    -1.70
    ſelves
    -1.69
     Houſe
    -1.69
    ſelf
    -1.66
    POSITIVE LOGITS
     (
    0.94
     for
    0.84
     "
    0.84
     or
    0.82
     to
    0.82
     
    0.81
    <eos>
    0.79
    ,
    0.78
     “
    0.77
     B
    0.76
    Activations Density 1.042%

    No Known Activations