© 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. 91046
    Prev
    Next
    INDEX
    Explanations

    src/sourcing

    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
    source
    -1.41
     source
    -1.22
    Source
    -1.15
     Source
    -1.05
    SOURCE
    -1.03
    sources
    -1.00
    sourced
    -0.97
    SOURCES
    -0.96
     SOURCE
    -0.93
    getSource
    -0.92
    POSITIVE LOGITS
     '\\;'
    0.94
     незавершена
    0.83
    AccessorTable
    0.82
     tartalomajánló
    0.75
    WriteBarrier
    0.74
    tvguidetime
    0.74
    (;;)
    0.73
     виправивши
    0.71
    Diweddarwch
    0.71
    expandindo
    0.70
    Activations Density 0.148%

    No Known Activations