© 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. 0-CLT-HP
    7. 91986
    Prev
    Next
    INDEX
    Explanations

    descriptive writing

    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
    ंदीखरीदारी
    -0.77
     Handling
    -0.75
     handling
    -0.72
    Personensuche
    -0.71
     صوتيه
    -0.70
    цездатний
    -0.70
     <=",
    -0.68
    Handling
    -0.67
    handling
    -0.67
     HANDLING
    -0.67
    POSITIVE LOGITS
     AssemblyCompany
    0.62
     pleaſure
    0.62
     themſelves
    0.57
     appartiennent
    0.54
     ThemeData
    0.52
     neceſſ
    0.52
     Ambiental
    0.49
    esterno
    0.48
     houſe
    0.48
     elä
    0.48
    Activations Density 0.047%

    No Known Activations