© 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. 12-RES-MATRYOSHKA-DC
    7. 22965
    Prev
    Next
    INDEX
    Explanations

    specific brand names and geographic locations associated with companies or entities

    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
     mxArray
    -0.88
     Nieto
    -0.84
    ://"
    -0.74
     Prat
    -0.74
     pii
    -0.73
    ritch
    -0.72
    Jain
    -0.71
     MPC
    -0.71
     Peterson
    -0.70
     fuel
    -0.69
    POSITIVE LOGITS
    AccessorTable
    1.04
     Manchester
    0.94
     manchester
    0.90
     Dex
    0.83
    Manchester
    0.81
     Monfieur
    0.78
     Alde
    0.78
     Johnny
    0.77
     Nader
    0.76
     LG
    0.75
    Activations Density 0.126%

    No Known Activations