© 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. 1-CLT-HP
    7. 13734
    Prev
    Next
    INDEX
    Explanations

    names

    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
     '\\;'
    -0.84
     ویکی‌پدیای
    -0.75
    клопе
    -0.74
    findpost
    -0.70
     correctes
    -0.64
    Artik
    -0.63
     écrans
    -0.58
     propOrder
    -0.57
    GeneratedCode
    -0.57
    ナブル
    -0.57
    POSITIVE LOGITS
    prepareStatement
    0.46
    y
    0.45
    ups
    0.44
    er
    0.43
    up
    0.41
    ie
    0.41
    al
    0.40
    OrNil
    0.40
    ies
    0.39
    n
    0.39
    Activations Density 0.019%

    No Known Activations