© 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. 71664
    Prev
    Next
    INDEX
    Explanations

    introduces a topic

    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
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.79
     intptr
    -0.66
    
    -0.57
     ExecuteAsync
    -0.56
    ernoo
    -0.55
    ]-->
    -0.54
    WireFormatLite
    -0.53
    الحياه
    -0.52
    Autoritní
    -0.50
     समीक्षक
    -0.50
    POSITIVE LOGITS
     Friends
    0.63
     Locks
    0.62
    RenderAtEndOf
    0.60
     interpretation
    0.57
     Furnace
    0.56
    friends
    0.56
     living
    0.56
     friends
    0.54
     Trust
    0.53
    Friends
    0.53
    Activations Density 0.000%

    No Known Activations