© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1960
    Prev
    Next
    INDEX
    Explanations

    Comparative

    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
     Comparative
    -0.71
     comparative
    -0.65
    Comparative
    -0.63
     mat
    -0.57
     teg
    -0.57
    jas
    -0.57
    Keys
    -0.56
     Kitz
    -0.54
    bed
    -0.52
    POP
    -0.52
    POSITIVE LOGITS
    theless
    0.61
    flakes
    0.59
    kaŭ
    0.57
    etcode
    0.56
     Locator
    0.54
    ñora
    0.54
    nastics
    0.54
    ябре
    0.54
    poptosis
    0.53
    orexia
    0.53
    Activations Density 0.114%

    No Known Activations