© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95551
    Prev
    Next
    INDEX
    Explanations

    java

    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
     '\\;'
    -0.88
    CodeAttribute
    -0.85
    KommentareTeilen
    -0.81
    pexpr
    -0.75
    urlpatterns
    -0.74
    BufferException
    -0.74
     HasFactory
    -0.74
     الحره
    -0.73
    featureID
    -0.73
    ynchronously
    -0.73
    POSITIVE LOGITS
     for
    0.47
     at
    0.46
    0.44
     on
    0.43
     covering
    0.43
     and
    0.43
     to
    0.42
     leading
    0.42
     of
    0.42
     raise
    0.42
    Activations Density 0.068%

    No Known Activations