© 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. 651
    Prev
    Next
    INDEX
    Explanations

    code referring to creating or modifying VPN sites

    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
    ValueStyle
    -0.77
     MonoBehaviour
    -0.70
     الحره
    -0.69
    XCT
    -0.68
     CWE
    -0.67
     którzy
    -0.66
     Spur
    -0.66
     bunt
    -0.63
    CHORUS
    -0.63
    ribune
    -0.62
    POSITIVE LOGITS
     client
    3.42
     Client
    3.19
    Client
    3.06
    client
    3.06
     clients
    3.05
     Clients
    2.92
     CLIENT
    2.80
    Clients
    2.64
    clients
    2.59
    CLIENT
    2.59
    Activations Density 0.055%

    No Known Activations