© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    references to storing or saving information

    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
    iented
    -0.58
    AsUp
    -0.57
    PMailer
    -0.57
    ofollow
    -0.56
    енча
    -0.53
    iecie
    -0.53
    UrlEncoded
    -0.51
     newItem
    -0.48
    @[+][
    -0.48
    __':
    -0.48
    POSITIVE LOGITS
     store
    3.97
    store
    3.66
     Store
    3.66
    Store
    3.53
     storage
    3.45
     stores
    3.42
     STORE
    3.33
     storing
    3.25
     Storage
    3.22
    STORE
    3.20
    Activations Density 1.392%

    No Known Activations