© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4518
    Prev
    Next
    INDEX
    Explanations

    diverse topics

    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
    SharedDtor
    -0.65
     CreateTagHelper
    -0.64
    numerusform
    -0.61
     استنادى
    -0.58
    principalColumn
    -0.57
    expandindo
    -0.56
    yntaxException
    -0.54
     Commencez
    -0.54
     AssemblyCompany
    -0.54
    wachs
    -0.53
    POSITIVE LOGITS
     sponsors
    0.58
     supporters
    0.53
    ReusableCell
    0.50
    Sponsors
    0.48
     to
    0.47
     Sponsors
    0.45
    llten
    0.43
     participants
    0.42
     advocates
    0.41
     contestants
    0.41
    Activations Density 0.004%

    No Known Activations