© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4679
    Prev
    Next
    INDEX
    Explanations

    references to cellular activity or processes involved in cell signaling, apoptosis, or regulation mechanisms

    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
    Negative Logits
     Action
    -1.55
     ACTION
    -1.48
     Actions
    -1.47
    Action
    -1.46
     action
    -1.45
    action
    -1.38
    Actions
    -1.34
    ACTION
    -1.34
     actions
    -1.27
    actions
    -1.25
    POSITIVE LOGITS
     activity
    1.70
     Activity
    1.45
     ACTIVITY
    1.35
    Activity
    1.33
    activity
    1.30
     actividad
    1.21
    activité
    1.10
     activité
    1.06
    ACTIVITY
    1.05
     atividade
    1.04
    Activations Density 0.025%

    No Known Activations