© 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. 3374
    Prev
    Next
    INDEX
    Explanations

    references to the concept of being persistent or ongoing

    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
    MENAFN
    -0.81
    AxisAlignment
    -0.80
     HomeComponent
    -0.79
    ActionCreators
    -0.78
    NRAS
    -0.77
    didSet
    -0.71
     TextAppearance
    -0.71
    oflavin
    -0.70
     Maru
    -0.69
    BeginInit
    -0.68
    POSITIVE LOGITS
     persistent
    2.86
     Persistent
    2.81
    persistent
    2.70
    Persistent
    2.67
     persistence
    2.64
     persist
    2.42
     Persistence
    2.30
     persisted
    2.25
    persist
    2.11
     persists
    2.05
    Activations Density 0.030%

    No Known Activations