© 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. 95184
    Prev
    Next
    INDEX
    Explanations

    personal

    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
    rungsseite
    -0.71
     AssemblyTitle
    -0.57
     répar
    -0.54
     pinulongan
    -0.52
     épaules
    -0.51
    WriteTagHelper
    -0.50
     vettor
    -0.49
    Kristi
    -0.49
     propias
    -0.49
    tér
    -0.48
    POSITIVE LOGITS
    addCriterion
    0.61
     Италијани
    0.59
     attacks
    0.59
    InitVars
    0.58
    mybatisplus
    0.57
    hoeddwyd
    0.54
     attacked
    0.54
     surla
    0.53
     transférez
    0.53
     estekak
    0.52
    Activations Density 0.001%

    No Known Activations