© 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. 95467
    Prev
    Next
    INDEX
    Explanations

    exam

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.65
    Exam
    -0.63
    WriteTagHelper
    -0.57
     romántica
    -0.54
    SpringRunner
    -0.52
     Exam
    -0.52
    évaluateur
    -0.48
     通販
    -0.46
     española
    -0.45
    gamepad
    -0.45
    POSITIVE LOGITS
     fieldNum
    0.57
    oredCriteria
    0.57
    pture
    0.57
    wareness
    0.56
    Datuak
    0.56
     sauve
    0.56
     Merr
    0.56
    ould
    0.55
    CppCodeGen
    0.55
     Horizons
    0.54
    Activations Density 0.067%

    No Known Activations