© 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. 40585
    Prev
    Next
    INDEX
    Explanations

    changes, trends

    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
    initializeApp
    -0.57
    XMLSchema
    -0.54
    mp
    -0.54
    gp
    -0.52
    rhosis
    -0.51
    wa
    -0.50
    ds
    -0.50
    db
    -0.49
    mesa
    -0.49
     архивлан
    -0.48
    POSITIVE LOGITS
    المناصب
    0.69
     Audiodateien
    0.64
     whereof
    0.63
     negroes
    0.61
    ActionCreators
    0.60
    pushFollow
    0.60
     CreateTagHelper
    0.60
    ⓧ
    0.58
    ClientRect
    0.57
     تضيفلها
    0.56
    Activations Density 0.058%

    No Known Activations