© 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. 1-RES-MATRYOSHKA-DC
    7. 941
    Prev
    Next
    INDEX
    Explanations

    references to molecular mechanisms involved in activation and silencing processes

    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
     betweenstory
    -0.55
    CHELL
    -0.52
    onoi
    -0.52
    slidesToShow
    -0.52
    ellschaft
    -0.51
     Donne
    -0.51
     Messer
    -0.51
    nios
    -0.51
     endIndex
    -0.50
     signal
    -0.49
    POSITIVE LOGITS
     activation
    3.75
     activated
    3.70
    activated
    3.45
     activate
    3.42
     Activation
    3.42
     activating
    3.31
     Activated
    3.28
    activation
    3.27
    Activation
    3.05
    activate
    3.03
    Activations Density 0.387%

    No Known Activations