© 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. 95552
    Prev
    Next
    INDEX
    Explanations

    do

    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
     do
    -0.66
    ,
    -0.48
    s
    -0.48
     (
    -0.47
    nya
    -0.43
    ness
    -0.41
    mäs
    -0.41
    d
    -0.39
    saving
    -0.38
     zien
    -0.37
    POSITIVE LOGITS
     houſe
    1.29
     purpoſe
    1.22
     pleaſure
    1.17
     ſtate
    1.11
     poffe
    1.10
     myſelf
    1.09
     Efq
    1.06
     Monfieur
    1.06
     Houſe
    1.05
     reaſon
    1.04
    Activations Density 0.025%

    No Known Activations