© 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. 95588
    Prev
    Next
    INDEX
    Explanations

    question/exclamation marks

    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
     myſelf
    -1.66
     itſelf
    -1.64
     Efq
    -1.48
    ſelves
    -1.41
     pleaſure
    -1.41
     purpoſe
    -1.41
     themſelves
    -1.39
     Majefty
    -1.38
     himſelf
    -1.37
    ſelf
    -1.34
    POSITIVE LOGITS
    ,
    1.15
    -
    1.14
     A
    1.13
     The
    1.13
    ↵↵
    1.11
    :
    1.11
     (
    1.09
    (
    1.07
     I
    1.05
     We
    1.05
    Activations Density 0.079%

    No Known Activations