© 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. 6082
    Prev
    Next
    INDEX
    Explanations

    specific patterns of code related to layout and size configurations

    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
    LookAnd
    -0.83
    ModelSerializer
    -0.74
     pleaſure
    -0.71
     AssemblyTitle
    -0.70
     NSCoder
    -0.70
    TagMode
    -0.67
    XMLSchema
    -0.66
    ^(@)
    -0.66
     Савезне
    -0.65
    AndEndTag
    -0.64
    POSITIVE LOGITS
     onPostExecute
    0.58
    ładka
    0.45
    Solu
    0.44
    many
    0.44
    NEP
    0.41
     muze
    0.41
    dead
    0.40
    Viele
    0.40
     TreeMap
    0.40
    燃
    0.40
    Activations Density 0.451%

    No Known Activations