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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41972
    Prev
    Next
    INDEX
    Explanations

    subjective adjectives

    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
    Datuak
    -0.98
    AndEndTag
    -0.95
     ExecuteAsync
    -0.91
     OFDb
    -0.91
     pinulongan
    -0.89
    boring
    -0.88
     Мексичка
    -0.88
     kasarigan
    -0.87
     EconPapers
    -0.87
    İstinadlar
    -0.86
    POSITIVE LOGITS
    ly
    0.83
    LY
    0.73
     true
    0.50
    emu
    0.49
    mstyle
    0.46
    τά
    0.46
    ian
    0.45
    ako
    0.45
    ed
    0.44
    ally
    0.44
    Activations Density 0.180%

    No Known Activations