© 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. 4-CLT-HP
    4. 2817
    Prev
    Next
    INDEX
    Explanations

    Mixed snippets of text

    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
    BufferException
    -0.66
    EndInit
    -0.54
    rophes
    -0.52
    יוחד
    -0.51
    ñal
    -0.51
    NameInMap
    -0.51
    MessageTagHelper
    -0.49
    ichio
    -0.49
    SourceChecksum
    -0.48
    Vidite
    -0.47
    POSITIVE LOGITS
    PyExc
    0.75
     modelAndView
    0.64
     ویکی‌پدیای
    0.63
     مشين
    0.62
    سطس
    0.61
    Remarque
    0.60
     digress
    0.59
     виправивши
    0.56
     resourceCulture
    0.56
    uttavia
    0.56
    Activations Density 0.019%

    No Known Activations