© 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. 45120
    Prev
    Next
    INDEX
    Explanations

    technical/chemistry language

    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
    WriteAttribute
    -0.81
    tagHelperRunner
    -0.81
    AddTagHelper
    -0.80
     aikaa
    -0.79
    MemoryWarning
    -0.78
    theless
    -0.78
    følgelig
    -0.77
    BeginInit
    -0.76
    WriteTagHelper
    -0.76
    parsedMessage
    -0.75
    POSITIVE LOGITS
     arg
    0.57
     sud
    0.53
     ad
    0.52
     age
    0.50
     uns
    0.50
    ╭
    0.47
     y
    0.46
     record
    0.46
     det
    0.45
     sub
    0.45
    Activations Density 0.034%

    No Known Activations