© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound, particularly "nitric" with varying degrees of activation

    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
    pośred
    -0.60
    ibatis
    -0.58
     plaisir
    -0.54
    stasia
    -0.52
     duty
    -0.50
     pubblici
    -0.49
    Tazama
    -0.49
     Resolución
    -0.49
     biais
    -0.48
    PETS
    -0.47
    POSITIVE LOGITS
    ric
    3.86
    RIC
    2.61
    rics
    2.22
    rik
    1.58
    ricate
    1.52
    rico
    1.52
     RIC
    1.49
    rica
    1.45
    rick
    1.39
    Ric
    1.38
    Activations Density 0.022%

    No Known Activations