© 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. 3395
    Prev
    Next
    INDEX
    Explanations

    references to metal or metal-containing compounds

    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
     Paper
    -0.83
    Paper
    -0.78
     paper
    -0.75
    paper
    -0.75
     PAPER
    -0.75
     Gold
    -0.71
    didSet
    -0.65
     onCreateView
    -0.65
    PAPER
    -0.65
    ]--;
    -0.65
    POSITIVE LOGITS
     metal
    2.17
    metal
    2.02
     Metal
    2.00
    Metal
    1.95
     METAL
    1.87
     métal
    1.66
    METAL
    1.49
     métallique
    1.41
     metals
    1.34
    金属
    1.29
    Activations Density 0.024%

    No Known Activations