© 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. 20-CLT-HP
    7. 71483
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · 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
    ParallelGroup
    -0.60
    COUVER
    -0.57
     nakalista
    -0.57
    urlpatterns
    -0.57
    zeera
    -0.50
    ImageIO
    -0.49
    findpost
    -0.49
    forName
    -0.49
    zew
    -0.48
    ])):
    -0.48
    POSITIVE LOGITS
    aarrggbb
    0.62
    onomía
    0.52
    ="@+
    0.51
     setUp
    0.48
    ainville
    0.48
    بح
    0.47
    spring
    0.47
    UIControlState
    0.47
    SharedCtor
    0.47
    ึ้น
    0.47
    Activations Density 0.000%

    No Known Activations