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. 14876
    Prev
    Next
    INDEX
    Explanations

    statements that contain the word "actually" after a pronoun

    oai_token-act-pair · gemini-2.0-flash

    actually

    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
     actually
    -2.06
    actually
    -1.92
     actual
    -1.78
     Actually
    -1.77
    Actually
    -1.70
    actual
    -1.64
     ACTUALLY
    -1.55
     Actual
    -1.54
    Actual
    -1.45
     ACTUAL
    -1.41
    POSITIVE LOGITS
    DoubleQuotes
    0.59
    tonode
    0.54
    bewerken
    0.51
    Filmographie
    0.51
    SocketAddress
    0.51
     okuyayım
    0.51
     initComponents
    0.48
     getRule
    0.48
    نامج
    0.48
    transQ
    0.47
    Activations Density 1.150%

    No Known Activations