© 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. 5-CLT-HP
    7. 876
    Prev
    Next
    INDEX
    Explanations

    code and technical content

    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
     pinulongan
    -0.83
    posedge
    -0.62
     становника
    -0.61
    mobileqq
    -0.60
    SupportActionBar
    -0.60
    BagLayout
    -0.57
     utafitiHapana
    -0.57
    piram
    -0.57
     onBind
    -0.55
    <bos>
    -0.53
    POSITIVE LOGITS
    EDA
    0.56
     DRS
    0.50
    omock
    0.49
    spraak
    0.48
    monium
    0.48
    platin
    0.47
     Chant
    0.47
     externally
    0.47
    chaos
    0.46
     chaos
    0.46
    Activations Density 0.002%

    No Known Activations