© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2978
    Prev
    Next
    INDEX
    Explanations

    publishing

    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
    writeField
    -0.58
     >=",
    -0.55
     beschik
    -0.54
     ProtoMessage
    -0.53
    λογία
    -0.52
     attentes
    -0.52
    ★★★★★
    -0.51
    niosek
    -0.51
    tifkan
    -0.51
     swallow
    -0.50
    POSITIVE LOGITS
     on
    0.98
    RefNanny
    0.76
    tagHelperRunner
    0.73
    AddTagHelper
    0.61
    ChildScrollView
    0.60
    SequentialGroup
    0.56
    DockStyle
    0.56
     تضيفلها
    0.55
    adaptiveStyles
    0.52
     typelib
    0.49
    Activations Density 0.003%

    No Known Activations