© 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. 21
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to manufacturing semiconductors using lithography and electron beams.

    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
    angliski
    -0.63
    czegóły
    -0.63
     jScrollPane
    -0.60
    CodedInputStream
    -0.59
    invokeLater
    -0.58
    ArrowToggle
    -0.57
    VYMaps
    -0.56
     encomp
    -0.56
    Zunanje
    -0.54
    SBATCH
    -0.53
    POSITIVE LOGITS
    hoge
    0.68
    ləş
    0.67
    ①
    0.59
     Jpn
    0.58
     hardly
    0.58
     personnels
    0.58
     Judging
    0.57
     indispensable
    0.57
     transparence
    0.57
    ≒
    0.56
    Activations Density 3.608%

    No Known Activations