© 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. 3702
    Prev
    Next
    INDEX
    Explanations

    references to VPN site resources within specific code and API contexts

    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
     protoimpl
    -0.56
    la
    -0.53
    le
    -0.52
    ab
    -0.52
    lat
    -0.50
    A
    -0.47
    et
    -0.46
    ob
    -0.45
    ke
    -0.45
    un
    -0.45
    POSITIVE LOGITS
     propOrder
    0.99
    RenderAtEndOf
    0.94
    usermodel
    0.84
     nakalista
    0.78
    ExtendWith
    0.77
     useStyles
    0.72
    ratulations
    0.71
    ViewImports
    0.71
    RunWith
    0.70
    essages
    0.69
    Activations Density 0.615%

    No Known Activations