© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    references to cache memory

    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
     ViewGroup
    -0.62
    FieldNumber
    -0.62
     initComponents
    -0.60
    IndentedString
    -0.58
     CanadaChoose
    -0.57
    parsedMessage
    -0.56
    initComponents
    -0.55
     Horn
    -0.55
    scriptcase
    -0.54
     Vrbo
    -0.52
    POSITIVE LOGITS
     cache
    4.66
    cache
    4.16
     Cache
    4.03
    Cache
    3.77
     caches
    3.48
     CACHE
    3.36
    CACHE
    3.30
     caching
    3.17
     cached
    2.98
    caches
    2.66
    Activations Density 0.008%

    No Known Activations