© 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. 5-CLT-HP
    7. 90939
    Prev
    Next
    INDEX
    Explanations

    code variables "u" "v"

    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
    fjspx
    -0.69
    setVerticalGroup
    -0.68
     Karab
    -0.61
     ComVisible
    -0.60
     resolution
    -0.59
    StoryboardSegue
    -0.59
    Diweddarwch
    -0.59
    rrggbb
    -0.57
    setupUi
    -0.57
    ReusableCell
    -0.57
    POSITIVE LOGITS
     consultato
    0.50
     móveis
    0.46
    Ane
    0.46
     tå
    0.45
     periódicos
    0.45
    мед
    0.44
     gång
    0.44
     portátiles
    0.43
     puertos
    0.43
     aikaa
    0.42
    Activations Density 0.015%

    No Known Activations