© 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. 1-CLT-HP
    7. 45952
    Prev
    Next
    INDEX
    Explanations

    Lakes

    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
     LAKE
    -1.39
     Lake
    -1.37
     lake
    -1.35
    Lake
    -1.32
     Lakes
    -1.22
     lakes
    -1.20
    lake
    -1.15
    LAKE
    -1.09
    Lakes
    -1.07
    lakes
    -1.01
    POSITIVE LOGITS
    ตร์
    0.53
     verrez
    0.52
     of
    0.51
    uesia
    0.50
     superiores
    0.48
    ulz
    0.46
     urbanas
    0.45
     gwiazd
    0.45
     cioccolato
    0.45
     cél
    0.45
    Activations Density 0.009%

    No Known Activations