© 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. 2-RES-MATRYOSHKA-DC
    7. 2946
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific brand or type of decorative or functional glass used in home or building design

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veratrol
    -0.68
    endphp
    -0.54
    Décès
    -0.48
     distanciation
    -0.47
     emerg
    -0.47
    titudine
    -0.47
    antMatchers
    -0.47
    istre
    -0.46
    dagog
    -0.46
     betal
    -0.45
    POSITIVE LOGITS
    ory
    4.13
    ORY
    3.53
    ories
    2.30
    ori
    1.95
    ORI
    1.74
    ORIES
    1.70
     ory
    1.70
    orie
    1.69
    oria
    1.67
    tory
    1.62
    Activations Density 0.011%

    No Known Activations