© 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. 2-RES-MATRYOSHKA-DC
    7. 5226
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blow" or references to blowing things up

    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
     Fermi
    -0.56
     Normdatei
    -0.55
     lactate
    -0.54
     Cartwright
    -0.54
    Arsenic
    -0.53
     Réponses
    -0.53
    Diverse
    -0.53
     propOrder
    -0.52
     Schicht
    -0.51
     sonre
    -0.51
    POSITIVE LOGITS
     blow
    3.89
    blow
    3.52
     Blow
    3.47
     blowing
    3.36
     blows
    3.34
     blown
    3.33
    Blow
    3.30
     blew
    3.22
    blowing
    2.73
    blown
    2.53
    Activations Density 0.006%

    No Known Activations