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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92270
    Prev
    Next
    INDEX
    Explanations

    expect

    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
    hat
    -0.80
     on
    -0.63
     in
    -0.60
     here
    -0.60
     of
    -0.57
     that
    -0.57
    ht
    -0.56
    .
    -0.55
    hata
    -0.54
     can
    -0.52
    POSITIVE LOGITS
    ValueStyle
    1.00
     disambiguazione
    1.00
    tagHelperRunner
    0.95
     betweenstory
    0.88
     itſelf
    0.86
     Савезне
    0.82
     виправивши
    0.81
     purpoſe
    0.81
     nahilalakip
    0.81
    expandindo
    0.79
    Activations Density 0.442%

    No Known Activations