© 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. 91034
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    Runner
    -0.45
     Lordships
    -0.44
    Yung
    -0.43
     lomb
    -0.42
    RTLD
    -0.42
    kiye
    -0.41
     Lino
    -0.41
     vred
    -0.40
     Lewin
    -0.40
     pretence
    -0.40
    POSITIVE LOGITS
    invokeLater
    0.65
    WriteTagHelper
    0.56
    Koordinaten
    0.56
     typelib
    0.55
     <<<<<<<<<<<<<<
    0.54
     JpaRepository
    0.54
    曖昧さ回避
    0.54
     المعيارى
    0.54
     Mo
    0.53
     testGet
    0.53
    Activations Density 0.010%

    No Known Activations