© 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. 95709
    Prev
    Next
    INDEX
    Explanations

    notice, list

    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
     Efq
    -1.45
     myſelf
    -1.34
     Houſe
    -1.30
     purpoſe
    -1.28
     itſelf
    -1.28
     pleaſure
    -1.27
     Monfieur
    -1.27
     houſe
    -1.27
    ſelf
    -1.25
     photolibrary
    -1.24
    POSITIVE LOGITS
    ,
    0.71
     to
    0.70
    .
    0.61
     -
    0.59
     that
    0.56
     (
    0.54
     like
    0.54
     as
    0.53
     –
    0.52
     at
    0.50
    Activations Density 0.730%

    No Known Activations