© 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. 1-CLT-HP
    7. 9236
    Prev
    Next
    INDEX
    Explanations

    legal and code

    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
     Chancery
    -1.67
     ویکی‌پدیا
    -0.64
     فريبيس
    -0.47
     AssemblyCulture
    -0.46
     SqlDbType
    -0.44
     onBind
    -0.42
     Silica
    -0.42
     TGF
    -0.41
    StoreMessageInfo
    -0.40
     Venetian
    -0.40
    POSITIVE LOGITS
     gynhyrchwyd
    0.73
    مصادر
    0.69
     CreateTagHelper
    0.67
    queryInterface
    0.66
     BoxFit
    0.66
    äsident
    0.65
     kasarigan
    0.64
    AndEndTag
    0.60
    érience
    0.59
    UnitTesting
    0.59
    Activations Density 0.012%

    No Known Activations