© 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. 13115
    Prev
    Next
    INDEX
    Explanations

    uses of the word "hold"

    oai_token-act-pair · gemini-2.0-flash

    hold

    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
    ScopeManager
    -0.52
    marginVertical
    -0.51
    mybatisplus
    -0.50
    Leve
    -0.49
    ConverterFactory
    -0.48
    leur
    -0.46
    née
    -0.45
    ).
    -0.45
    intes
    -0.45
    diad
    -0.45
    POSITIVE LOGITS
    <bos>
    1.10
    contentLoaded
    0.74
     Wicidata
    0.63
     <>",
    0.60
    ^(@)
    0.60
    InitVars
    0.60
    łyn
    0.59
    iterraneo
    0.59
     becauſe
    0.58
    اشتم
    0.58
    Activations Density 2.342%

    No Known Activations