Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97880
    Prev
    Next
    INDEX
    Explanations

    lights

    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
     lights
    -1.25
     LIGHTS
    -0.92
     Lights
    -0.89
     lighting
    -0.83
     Lighting
    -0.83
    MES
    -0.74
    Lights
    -0.69
     Mes
    -0.68
    Mes
    -0.68
     MES
    -0.67
    POSITIVE LOGITS
    omeness
    0.65
    moke
    0.63
     nahilalakip
    0.61
    SourceChecksum
    0.60
    انيف
    0.60
    BeginContext
    0.59
    StructEnd
    0.59
    awaiter
    0.57
    resave
    0.56
    RRect
    0.56
    Activations Density 0.160%

    No Known Activations