© 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. 96107
    Prev
    Next
    INDEX
    Explanations

    me and colon

    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
    WriteBarrier
    -0.90
    ContentAsync
    -0.68
    Биография
    -0.65
    Jeografia
    -0.64
    GEBURTSDATUM
    -0.62
    chartInstance
    -0.60
    WriteAttribute
    -0.60
    Hochspringen
    -0.60
    Архівовано
    -0.59
    :✨
    -0.59
    POSITIVE LOGITS
    onas
    0.46
    unary
    0.45
     nhan
    0.44
     plant
    0.43
    grpc
    0.42
     dac
    0.42
    fork
    0.41
    าศ
    0.41
    ons
    0.40
     mand
    0.40
    Activations Density 0.005%

    No Known Activations