© 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. 1050
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     AssemblyTitle
    -1.06
     beginnetje
    -0.88
    Datuak
    -0.86
    AntiForgeryToken
    -0.83
     AssemblyVersion
    -0.83
     виправивши
    -0.82
    AndroidJUnit
    -0.81
     AspNetCore
    -0.80
     الحره
    -0.77
    رشف
    -0.76
    POSITIVE LOGITS
     Camp
    0.44
    gouv
    0.43
    docx
    0.42
    ytt
    0.42
     Bartolo
    0.41
     Beau
    0.40
    дует
    0.40
     Car
    0.40
     sam
    0.39
     g
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.