© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound involved in neural signaling

    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
     Tro
    -0.58
     TTS
    -0.56
    tro
    -0.53
     pistol
    -0.51
    Tro
    -0.49
    equi
    -0.49
    θο
    -0.49
    liebte
    -0.49
     gun
    -0.48
    eamento
    -0.48
    POSITIVE LOGITS
     trop
    3.25
     Trop
    2.86
    trop
    2.83
    Trop
    2.77
     TROP
    1.64
     tropics
    1.11
     tropic
    1.07
     trophies
    0.81
     troppo
    0.79
     Tropical
    0.72
    Activations Density 0.002%

    No Known Activations