© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    references to messenger RNA (mRNA) levels

    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
     DNA
    -0.65
    .$.
    -0.63
     DN
    -0.63
    otrop
    -0.61
     Miel
    -0.59
     Bie
    -0.57
    Bie
    -0.57
    ә
    -0.57
     bem
    -0.56
    ühm
    -0.56
    POSITIVE LOGITS
     mRNA
    2.48
    mRNA
    2.05
    abestanden
    0.93
     messenger
    0.81
    ecuzione
    0.80
     transcript
    0.79
    Morrison
    0.76
     Morrison
    0.72
    ształ
    0.71
     Messenger
    0.70
    Activations Density 0.004%

    No Known Activations