© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3230
    Prev
    Next
    INDEX
    Explanations

    special events and committees

    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
     special
    -1.02
    special
    -0.92
    Special
    -0.83
     Special
    -0.81
    twimg
    -0.79
    יוחד
    -0.76
     especial
    -0.76
    SPECIAL
    -0.74
    Especial
    -0.74
     SPECIAL
    -0.72
    POSITIVE LOGITS
    SPATH
    0.66
    oplasty
    0.46
    ness
    0.45
    ReferenceEquals
    0.44
     dimensioni
    0.44
    ActionCreators
    0.44
    AttributeName
    0.43
     répondu
    0.43
     fallu
    0.42
    المشاركات
    0.42
    Activations Density 0.004%

    No Known Activations