© 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. 4-CLT-HP
    7. 2586
    Prev
    Next
    INDEX
    Explanations

    since

    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
    ftagPool
    -0.74
    Демографія
    -0.70
    #+#
    -0.69
    +#+#
    -0.67
     >=",
    -0.66
     متعلقه
    -0.66
     Chwiliwch
    -0.65
     للمعارف
    -0.64
    setVerticalGroup
    -0.64
    windowFixed
    -0.61
    POSITIVE LOGITS
     you
    0.49
     first
    0.47
    unächst
    0.46
    moveToFirst
    0.46
    你来
    0.46
    ်
    0.46
    spender
    0.46
    yonel
    0.45
    HasForeignKey
    0.44
    Lur
    0.42
    Activations Density 0.009%

    No Known Activations