© 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. 5-CLT-HP
    7. 953
    Prev
    Next
    INDEX
    Explanations

    company updates and announcements

    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
     فريبيس
    -0.75
     المعيارى
    -0.68
     jScrollPane
    -0.67
     doInBackground
    -0.66
     iprot
    -0.62
    __":
    -0.62
     GenerationType
    -0.60
      (
    -0.60
    ViewImports
    -0.59
    <bos>
    -0.57
    POSITIVE LOGITS
    endpush
    0.63
     gddr
    0.54
     already
    0.51
     Planeta
    0.51
    coroutines
    0.51
    getCmp
    0.50
    esModule
    0.49
    Different
    0.49
    Another
    0.48
     Otro
    0.48
    Activations Density 0.001%

    No Known Activations