© 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. 16019
    Prev
    Next
    INDEX
    Explanations

    possess

    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
    уда
    -0.42
    -
    -0.42
    شار
    -0.41
     demais
    -0.41
    ubre
    -0.40
     mesmo
    -0.40
     fordi
    -0.39
     κάν
    -0.39
     صوتيه
    -0.38
     of
    -0.38
    POSITIVE LOGITS
     ſeveral
    0.90
     Efq
    0.82
     purpoſe
    0.78
     '\\;'
    0.77
     Majefty
    0.75
    ulemon
    0.74
     a
    0.74
     diſt
    0.73
     ſmall
    0.73
     ſta
    0.71
    Activations Density 0.008%

    No Known Activations