© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12269
    Prev
    Next
    INDEX
    Explanations

    both

    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
    fjspx
    -0.56
     dAtA
    -0.47
    gebob
    -0.47
    InstrumentedTest
    -0.44
    +#+#
    -0.44
     MonoBehaviour
    -0.44
    tagext
    -0.42
    WEBPACK
    -0.41
    interopRequire
    -0.41
     JScrollPane
    -0.41
    POSITIVE LOGITS
     synag
    0.66
     '\\;'
    0.66
     churches
    0.62
     tremp
    0.59
     mosques
    0.59
     civilizations
    0.59
     empires
    0.59
     municipalities
    0.58
     monasteries
    0.58
     theatres
    0.57
    Activations Density 0.011%

    No Known Activations