© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2330
    Prev
    Next
    INDEX
    Explanations

    online posts/articles

    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
     OFDb
    -0.55
     offense
    -0.54
     المعيارى
    -0.54
    出版年
    -0.53
    참고
    -0.52
     استنادى
    -0.52
    <bos>
    -0.50
    SpringRunner
    -0.50
     xét
    -0.50
    aktur
    -0.50
    POSITIVE LOGITS
    getColumnIndex
    0.60
     nemlig
    0.60
    SharedCtor
    0.55
    FieldDescriptor
    0.53
    AnchorStyles
    0.50
    yntaxException
    0.50
     AssemblyCulture
    0.49
    ]-->
    0.49
    doe
    0.49
     Reverso
    0.48
    Activations Density 0.000%

    No Known Activations