© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 453
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to specific topics, including personal names, companies, sports, locations, government, and crime

    oai_token-act-pair · gemini-2.0-flash
    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
    enumi
    -0.50
    SpringRunner
    -0.47
    SharedDtor
    -0.41
    </s>
    -0.40
    ̈́
    -0.40
     CCM
    -0.39
    Fernseh
    -0.38
     AssemblyTitle
    -0.37
    %")
    -0.37
    Wut
    -0.37
    POSITIVE LOGITS
    IsContent
    0.84
    GeneratedCode
    0.80
    verifyException
    0.75
    httphttps
    0.74
     saites
    0.74
    TintMode
    0.71
    UnusedPrivate
    0.68
    
    0.68
    ValueGenerated
    0.66
     noDo
    0.66
    Activations Density 13.845%

    No Known Activations