© 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. 18-RES-MATRYOSHKA-DC
    7. 1138
    Prev
    Next
    INDEX
    Explanations

    language related to semiconductor design and fabrication, particularly CMOS technology with polysilicon gates and metal gate electrodes and their properties.

    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.18.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.18.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
    UrlResolution
    -0.61
     Himo
    -0.57
     Zulu
    -0.52
     Chwiliwch
    -0.50
    IARC
    -0.50
     joaat
    -0.50
    kheim
    -0.50
    Geplaatst
    -0.49
     BoxFit
    -0.49
    ropractor
    -0.49
    POSITIVE LOGITS
     chip
    0.93
     Chip
    0.85
    Chip
    0.84
    chip
    0.79
     semiconductor
    0.79
     Chips
    0.77
     silicon
    0.76
     wafer
    0.75
     etching
    0.75
     chips
    0.74
    Activations Density 1.241%

    No Known Activations