© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15580
    Prev
    Next
    INDEX
    Explanations

    mentions of the security and integrity of data transmission protocols, specifically related to SSL, TLS, or general system compromises

    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
    SharedCtor
    -0.56
     мәкал
    -0.55
    Copied
    -0.51
     Boles
    -0.49
     Rox
    -0.49
    Uninitialized
    -0.48
    цыі
    -0.48
    vr
    -0.48
    ConstraintMaker
    -0.48
    AdapterView
    -0.47
    POSITIVE LOGITS
     compromised
    1.91
    compromised
    1.30
     compromising
    1.00
     confounding
    0.82
    compromising
    0.81
     Comprom
    0.75
    ulmuş
    0.75
     confounded
    0.72
     متعلقه
    0.72
    ruptedException
    0.70
    Activations Density 0.007%

    No Known Activations