© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3696
    Prev
    Next
    INDEX
    Explanations

    Scientific studies

    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
     results
    -0.60
     pilot
    -0.59
     result
    -0.57
     gepubliceerd
    -0.52
    interopRequire
    -0.50
     conduct
    -0.50
    结果
    -0.50
    NameInMap
    -0.49
     referenties
    -0.49
    WithIOException
    -0.49
    POSITIVE LOGITS
    \{\\
    0.63
     StringTokenizer
    0.57
    awtextra
    0.55
     الحره
    0.53
    SpringBootTest
    0.53
     culturelle
    0.52
     AssemblyTitle
    0.52
    tlement
    0.51
    faatkan
    0.51
     médicale
    0.50
    Activations Density 0.001%

    No Known Activations