© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    the word "holding"

    oai_token-act-pair · gemini-2.0-flash

    holding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     holding
    -1.49
    holding
    -1.41
    Holding
    -1.38
     Holding
    -1.37
     holdings
    -0.86
    holdings
    -0.85
     bearing
    -0.68
     blocking
    -0.66
     carrying
    -0.66
     standing
    -0.64
    POSITIVE LOGITS
    <bos>
    1.05
     متعلقه
    0.71
    PositiveButton
    0.65
    AddHtmlAttribute
    0.64
     unknownFields
    0.63
    binant
    0.63
    ExtendWith
    0.62
    spesies
    0.61
     kasarigan
    0.58
     circulate
    0.57
    Activations Density 3.318%

    No Known Activations