© 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. 46101
    Prev
    Next
    INDEX
    Explanations

    policy

    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
    ValueStyle
    -0.82
     >=",
    -0.75
    +#+#
    -0.68
    BeginContext
    -0.63
    ]$}
    -0.62
     &___
    -0.60
    fjspx
    -0.60
     <<<<<<<<<<<<<<
    -0.60
    MemoryWarning
    -0.59
    zarchiwizowane
    -0.59
    POSITIVE LOGITS
    createCanvas
    0.55
    ั่ว
    0.44
     ویکی‌پدیای
    0.44
     niches
    0.44
    Aprend
    0.44
     közül
    0.44
     felb
    0.43
    bauer
    0.43
    pilar
    0.42
    ensch
    0.42
    Activations Density 0.009%

    No Known Activations