© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    code segments related to setting and managing memory pool sizes

    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
     height
    -1.43
     Height
    -1.38
    height
    -1.34
    width
    -1.31
     width
    -1.29
     HEIGHT
    -1.23
    Height
    -1.22
    HEIGHT
    -1.17
     heights
    -1.08
     Width
    -1.08
    POSITIVE LOGITS
    size
    3.20
     size
    2.97
    Size
    2.92
     Size
    2.86
    SIZE
    2.53
     SIZE
    2.52
     sizes
    2.36
    sized
    2.23
     Sizes
    2.08
    sizes
    2.06
    Activations Density 0.400%

    No Known Activations