© 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. 4-CLT-HP
    7. 4379
    Prev
    Next
    INDEX
    Explanations

    .

    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
    WithIOException
    -0.85
    undred
    -0.65
    jectile
    -0.63
     Савезне
    -0.63
    ÁG
    -0.62
    ]='\
    -0.62
    RoutingModule
    -0.61
    interopRequire
    -0.60
    jectures
    -0.60
    ousands
    -0.60
    POSITIVE LOGITS
    He
    0.53
    His
    0.52
    by
    0.48
    Company
    0.48
    By
    0.48
    AddTagHelper
    0.45
    ↵
    0.44
    ladolid
    0.42
    Hand
    0.41
    Co
    0.39
    Activations Density 0.003%

    No Known Activations