© 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. 4-CLT-HP
    4. 2673
    Prev
    Next
    INDEX
    Explanations

    software/programming

    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
    án
    -0.63
    ian
    -0.54
    ekyll
    -0.54
    WEBPACK
    -0.54
    aky
    -0.53
    ática
    -0.50
    anyon
    -0.49
    putBoolean
    -0.48
    rawDesc
    -0.48
     Jekyll
    -0.48
    POSITIVE LOGITS
    UserScript
    0.78
     يتيمه
    0.73
    ="@+
    0.66
    setVerticalGroup
    0.64
    ThroughAttribute
    0.59
    ResumeLayout
    0.57
     estimés
    0.57
    ViewImports
    0.56
    MLLoader
    0.55
    shire
    0.54
    Activations Density 0.004%

    No Known Activations