© 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. 16001
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/names

    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
    -0.76
     Reſ
    -0.76
     becauſe
    -0.75
    POC
    -0.73
     Jefus
    -0.72
    findpost
    -0.71
    peka
    -0.71
     viſ
    -0.71
     POC
    -0.70
     itſelf
    -0.70
    POSITIVE LOGITS
     noDo
    0.59
     of
    0.53
    AndEndTag
    0.50
     voldo
    0.50
    MessageTagHelper
    0.47
    __*/
    0.47
    WithIOException
    0.44
    '][]
    0.44
     vær
    0.43
     berupa
    0.43
    Activations Density 0.350%

    No Known Activations