© 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. 10812
    Prev
    Next
    INDEX
    Explanations

    val

    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
    men
    -0.58
    ings
    -0.55
    INGS
    -0.52
    pan
    -0.48
    id
    -0.47
     petto
    -0.46
    ob
    -0.46
    ToString
    -0.45
    op
    -0.43
    bo
    -0.43
    POSITIVE LOGITS
    MLLoader
    0.83
     препратки
    0.75
     متعلقه
    0.66
     հղումներ
    0.64
    koneksi
    0.64
     WebDriverWait
    0.63
    ItemBackground
    0.63
    TargetException
    0.61
    InputBorder
    0.61
    новниш
    0.61
    Activations Density 0.086%

    No Known Activations