© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92660
    Prev
    Next
    INDEX
    Explanations

    scientific and technical topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.70
     bezeichneter
    -0.67
     Noto
    -0.63
     ſtate
    -0.63
    PUBLISH
    -0.62
    idamente
    -0.61
    ients
    -0.60
    
    -0.60
    expandindo
    -0.60
     preſent
    -0.60
    POSITIVE LOGITS
    belea
    0.55
    で見る
    0.44
     braccio
    0.43
     and
    0.42
    manes
    0.41
     braccia
    0.40
    ,
    0.40
    offsetof
    0.39
    NamedQuery
    0.39
     gained
    0.37
    Activations Density 0.003%

    No Known Activations