© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23847
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce specific examples or elaborations in academic writing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    XtraGrid
    -0.60
     PhpStorm
    -0.57
    dieu
    -0.55
    нтен
    -0.54
    addElement
    -0.52
    SharedDtor
    -0.51
    IComponent
    -0.50
     PropTypes
    -0.49
    TURE
    -0.49
    Blender
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.75
    脚注の使い方
    0.67
    кож
    0.65
    InvalidProtocol
    0.61
    fjspx
    0.60
    calça
    0.57
    tdessen
    0.57
     vielmehr
    0.54
    Viitteet
    0.54
    Hintergrund
    0.54
    Activations Density 0.020%

    No Known Activations