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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11028
    Prev
    Next
    INDEX
    Explanations

    Concept of control

    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
     Controls
    -0.77
     control
    -0.76
     controls
    -0.75
     Control
    -0.73
    control
    -0.71
    Controls
    -0.65
     CONTROL
    -0.64
    IBarButtonItem
    -0.64
    Control
    -0.63
    XDECREF
    -0.62
    POSITIVE LOGITS
     occidentale
    0.43
     importation
    0.43
     AssemblyProduct
    0.41
    aik
    0.40
     semn
    0.39
    umptive
    0.39
     onFailure
    0.38
     avvic
    0.38
     imports
    0.38
     emigration
    0.38
    Activations Density 0.006%

    No Known Activations