© 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. 60
    Prev
    Next
    INDEX
    Explanations

    references to the process of creating, cloning, or manipulating objects and operators in programming or quantum physics

    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
     maxn
    -0.90
     defStyle
    -0.84
    maxn
    -0.80
     sostanza
    -0.80
     CURIAM
    -0.79
    لينا
    -0.78
    borderColor
    -0.78
     whiteColor
    -0.78
     poteva
    -0.75
    atmosfera
    -0.75
    POSITIVE LOGITS
     take
    1.15
    take
    1.11
     build
    1.09
     use
    1.05
     release
    1.03
     BUILD
    1.00
    make
    0.98
     send
    0.98
     create
    0.97
    Create
    0.96
    Activations Density 17.613%

    No Known Activations