© 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. 4319
    Prev
    Next
    INDEX
    Explanations

    IP addresses and network protocol identifiers in technical text

    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
    Datuak
    -0.84
     createStore
    -0.76
     Efq
    -0.73
    RegisterType
    -0.69
    pentine
    -0.68
     fince
    -0.65
    oxone
    -0.65
     Chrif
    -0.65
     tfsi
    -0.65
     Chriftian
    -0.65
    POSITIVE LOGITS
    IP
    3.30
     IP
    3.25
    ip
    2.88
     ip
    2.72
    Ip
    2.25
    IPs
    2.20
     Ip
    2.06
     IPs
    2.05
    ips
    1.66
    IpAddress
    1.50
    Activations Density 0.232%

    No Known Activations