© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13837
    Prev
    Next
    INDEX
    Explanations

    the control elements within a user interface context

    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
    SourceChecksum
    -0.66
    GIVEREF
    -0.62
     transfieras
    -0.55
    EndGlobalSection
    -0.54
     Lang
    -0.52
    CodedInputStream
    -0.52
    JsonHelper
    -0.52
     CreateTagHelper
    -0.51
    styleType
    -0.51
    جستارهای
    -0.50
    POSITIVE LOGITS
    Control
    1.92
     Control
    1.23
    CONTROL
    0.90
     CONTROL
    0.80
    FormControl
    0.68
     INTERESAR
    0.61
    },{
    0.59
     fubject
    0.59
     TestBed
    0.58
    WireFormat
    0.58
    Activations Density 0.006%

    No Known Activations