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. 16092
    Prev
    Next
    INDEX
    Explanations

    job descriptions containing the word "time" modified by "full" or "part"

    oai_token-act-pair · gemini-2.0-flash

    part/full time

    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
     kasarigan
    -0.76
     ujednoznacz
    -0.72
    __':
    -0.69
    BagLayout
    -0.68
    PRWEB
    -0.66
    VersionUID
    -0.65
    EndContext
    -0.64
    abestanden
    -0.63
    TagMode
    -0.62
    DispatchToProps
    -0.59
    POSITIVE LOGITS
     time
    0.68
    time
    0.64
    Time
    0.57
    jooq
    0.53
    styleType
    0.52
     Time
    0.51
     TIME
    0.51
    TIME
    0.50
    タイム
    0.50
     tijd
    0.45
    Activations Density 0.254%

    No Known Activations