Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12857
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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
     worn
    -0.76
     nahilalakip
    -0.54
     otomatig
    -0.54
     lenker
    -0.54
     دیکھیے
    -0.54
    matchCondition
    -0.53
     House
    -0.52
    worn
    -0.52
     Gson
    -0.50
     getCity
    -0.50
    POSITIVE LOGITS
    calientes
    0.58
    èlement
    0.53
    awtextra
    0.51
    μφωνα
    0.49
    Skocz
    0.48
    揄
    0.48
    первых
    0.48
     dekor
    0.47
    ($__
    0.47
    dafri
    0.45
    Activations Density 0.262%

    No Known Activations