© 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. 5-CLT-HP
    7. 6223
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     the
    -0.63
     a
    -0.53
     some
    -0.49
    WebControls
    -0.49
    saraba
    -0.48
     our
    -0.48
    );*/
    -0.47
    ,
    -0.47
     this
    -0.46
    jong
    -0.46
    POSITIVE LOGITS
     perſon
    0.69
     Diſ
    0.66
     auffi
    0.65
     houſe
    0.64
     Inſ
    0.63
     Monfieur
    0.63
     Reſ
    0.62
     pleaſure
    0.62
     Jefus
    0.61
     ſtate
    0.61
    Activations Density 0.015%

    No Known Activations