© 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. 71287
    Prev
    Next
    INDEX
    Explanations

    Mixed content/text

    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
    ardless
    -0.66
     Anſ
    -0.64
     houſe
    -0.63
     pleaſure
    -0.63
     Perſ
    -0.63
     Eſ
    -0.62
    SizeF
    -0.62
     Reſ
    -0.61
    ρών
    -0.60
     Majefty
    -0.60
    POSITIVE LOGITS
    Šaltiniai
    0.49
    )))));
    0.44
    FontStyle
    0.44
    Cyfeiriadau
    0.43
     GAP
    0.42
    SuccessListener
    0.42
    disco
    0.42
    
    0.42
    ContentAsync
    0.41
    writeField
    0.41
    Activations Density 0.002%

    No Known Activations