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. 14749
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "that"

    oai_token-act-pair · gemini-2.0-flash

    that

    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
     CreateTagHelper
    -0.65
     Taktlose
    -0.65
     تانيه
    -0.64
    UIControlState
    -0.64
    脚注の使い方
    -0.64
     مشين
    -0.63
     onCreateView
    -0.62
     AssemblyCulture
    -0.61
     resourceCulture
    -0.60
    +#+#
    -0.59
    POSITIVE LOGITS
     is
    0.55
     will
    0.54
     aggiunto
    0.47
    yntaxException
    0.46
    MediaStore
    0.46
    JFrame
    0.46
    Ệ
    0.46
     works
    0.45
    Hentet
    0.45
    van
    0.44
    Activations Density 2.237%

    No Known Activations