© 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. 95134
    Prev
    Next
    INDEX
    Explanations

    fast

    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
     copies
    -0.58
     segments
    -0.52
     equivalents
    -0.50
     arrangements
    -0.49
    copies
    -0.47
     rés
    -0.46
     copias
    -0.46
     analogs
    -0.46
     analogues
    -0.46
     plans
    -0.45
    POSITIVE LOGITS
    AccessorTable
    0.77
    IonicModule
    0.65
    EndGlobalSection
    0.64
    ulaski
    0.63
    stateProvider
    0.63
    CloseOperation
    0.61
    WindowConstants
    0.61
    onOptions
    0.61
     JFrame
    0.60
     MaterialApp
    0.60
    Activations Density 0.001%

    No Known Activations