© 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. 0-CLT-HP
    4. 40962
    Prev
    Next
    INDEX
    Explanations

    About data and sources

    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
    InjectAttribute
    -0.92
     itſelf
    -0.90
     raiſ
    -0.86
     Anſ
    -0.84
     Reſ
    -0.82
    tagHelperRunner
    -0.80
     anſ
    -0.79
     femininas
    -0.79
    CloseOperation
    -0.77
     cauſe
    -0.76
    POSITIVE LOGITS
     ‘
    0.63
    ↵↵
    0.60
     (
    0.60
     “
    0.57
    .
    0.55
     p
    0.54
     alt
    0.54
     
    0.54
     les
    0.54
     l
    0.53
    Activations Density 1.090%

    No Known Activations