© 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. 92359
    Prev
    Next
    INDEX
    Explanations

    tragic events or heritage

    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
     heritage
    -1.20
    Heritage
    -1.20
    heritage
    -1.17
    RenderAtEndOf
    -1.15
     Heritage
    -1.09
     Efq
    -1.01
    SequentialGroup
    -0.98
     myſelf
    -0.98
     nakalista
    -0.96
    يميديا
    -0.95
    POSITIVE LOGITS
     e
    0.61
     
    0.60
    ,
    0.58
     (
    0.57
     as
    0.57
     index
    0.56
     and
    0.55
     pot
    0.55
     in
    0.54
     I
    0.54
    Activations Density 0.048%

    No Known Activations