© 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. 95778
    Prev
    Next
    INDEX
    Explanations

    rerum

    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
     houſe
    -1.50
     δὲ
    -1.45
     quæ
    -1.44
     purpoſe
    -1.42
     ſever
    -1.41
     itſelf
    -1.41
     ſtate
    -1.41
     myſelf
    -1.41
     Jefus
    -1.40
     faſt
    -1.40
    POSITIVE LOGITS
    ggars
    0.65
    spyOn
    0.62
     Audiodateien
    0.62
     /\.
    0.60
    ی
    0.59
    elashes
    0.56
    i
    0.56
     ט
    0.56
    hydrogenase
    0.56
    termilk
    0.56
    Activations Density 0.187%

    No Known Activations