© 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. 78106
    Prev
    Next
    INDEX
    Explanations

    Technical/Research 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
    complexContent
    -0.94
    IUrlHelper
    -0.80
    Personendaten
    -0.78
    ]='\
    -0.77
    
    -0.76
    λογία
    -0.76
    SharedDtor
    -0.75
    المناصب
    -0.73
    __;
    -0.70
    :✨
    -0.68
    POSITIVE LOGITS
    modb
    0.37
     av
    0.36
     au
    0.36
     CUM
    0.32
     avo
    0.32
    coste
    0.31
     aeruginosa
    0.30
    owohl
    0.28
     ader
    0.27
    Au
    0.26
    Activations Density 0.000%

    No Known Activations