© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    references to the crystalline structure or form of a substance

    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
     Audiodateien
    -0.66
    rolla
    -0.61
    ]._
    -0.59
    htë
    -0.59
     TAMBIÉN
    -0.58
     Nusa
    -0.58
    ARTER
    -0.57
     Miquel
    -0.57
     Ayu
    -0.57
    ishment
    -0.56
    POSITIVE LOGITS
     mono
    2.55
     Mono
    2.55
    mono
    2.25
    Mono
    2.20
     MONO
    1.79
    MONO
    1.62
     monoclonal
    1.40
     monolayer
    1.38
     Unity
    1.22
     monopo
    1.19
    Activations Density 0.031%

    No Known Activations