© 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. 38885
    Prev
    Next
    INDEX
    Explanations

    process

    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
     Process
    -1.27
    process
    -1.23
     process
    -1.19
    Process
    -1.15
     PROCESS
    -1.10
     Processes
    -0.98
     processes
    -0.98
    PROCESS
    -0.98
    processes
    -0.95
     proceso
    -0.95
    POSITIVE LOGITS
     generator
    0.48
    TestingModule
    0.46
     engine
    0.46
     throttle
    0.42
     injector
    0.41
    endif
    0.41
    cit
    0.41
     finder
    0.40
     specchio
    0.40
     alarm
    0.39
    Activations Density 0.764%

    No Known Activations