© 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. 2793
    Prev
    Next
    INDEX
    Explanations

    technical jargon for electrical wiring

    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
     defaultstate
    -0.72
    usercontent
    -0.59
    bewerken
    -0.52
     Burch
    -0.52
    édie
    -0.52
    __':
    -0.51
    nessed
    -0.51
    SourceChecksum
    -0.51
    WebControls
    -0.50
    igata
    -0.50
    POSITIVE LOGITS
     cable
    1.54
     cables
    1.46
    Cable
    1.35
     Cable
    1.34
    cable
    1.33
     wire
    1.29
     wires
    1.28
     Cables
    1.28
     CABLE
    1.27
     kabel
    1.18
    Activations Density 0.229%

    No Known Activations