© 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. 22-RES-MATRYOSHKA-DC
    7. 1671
    Prev
    Next
    INDEX
    Explanations

    the word "we" within mathematical or academic research papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provided
    -0.60
    provided
    -0.50
     verwendeten
    -0.47
     providing
    -0.47
     we
    -0.47
    viders
    -0.45
     PROVIDED
    -0.45
     utilizamos
    -0.45
     tương
    -0.45
     assessed
    -0.45
    POSITIVE LOGITS
     estekak
    0.77
     MainAxisSize
    0.75
    IVEREF
    0.74
    IntoConstraints
    0.73
     المعيارى
    0.73
    DockStyle
    0.73
    ंदीखरीदारी
    0.72
    脚注の使い方
    0.71
    Datuak
    0.70
    setVerticalGroup
    0.69
    Activations Density 0.352%

    No Known Activations