© 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. 97170
    Prev
    Next
    INDEX
    Explanations

    random text excerpts

    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
    ########.
    -0.73
    findpost
    -0.70
     MainAxisSize
    -0.69
    i
    -0.66
    IContainer
    -0.63
     "..\..\..\
    -0.63
    jooq
    -0.62
     ContentValues
    -0.58
     Seder
    -0.58
     Langmuir
    -0.58
    POSITIVE LOGITS
     مشين
    0.51
    ations
    0.48
    出身
    0.46
    Pautan
    0.45
    lihatan
    0.44
    Rujuakan
    0.43
    utilise
    0.43
     سكانية
    0.42
    SupportActionBar
    0.41
    freopen
    0.41
    Activations Density 0.820%

    No Known Activations