Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16119
    Prev
    Next
    INDEX
    Explanations

    words that are related to pregnancy and women's health in the context of clinical trials

    oai_token-act-pair · gemini-2.0-flash

    Pregnancy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inya
    -0.49
     خاطر
    -0.48
    TagMode
    -0.48
     ca
    -0.47
     gy
    -0.47
    sela
    -0.46
    ksh
    -0.45
    NLS
    -0.44
    yeli
    -0.44
    ца
    -0.43
    POSITIVE LOGITS
    dflare
    0.71
     MotionEvent
    0.69
     AssemblyCulture
    0.64
     للاسماء
    0.62
     StatelessWidget
    0.62
    AnchorTagHelper
    0.62
    execSQL
    0.60
     Chord
    0.59
     onPostExecute
    0.59
     समीक्षक
    0.59
    Activations Density 7.317%

    No Known Activations