© 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. 6-RES-MATRYOSHKA-DC
    7. 805
    Prev
    Next
    INDEX
    Explanations

    gibberish found in HTML source code as well as certain numbers

    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
     BEM
    -0.66
     saurait
    -0.63
    spender
    -0.61
    StoreMessageInfo
    -0.60
     PopupWindow
    -0.60
    цездатний
    -0.59
    ✨:
    -0.58
    قایناقلار
    -0.58
    йтинг
    -0.56
     rhestr
    -0.56
    POSITIVE LOGITS
    #
    0.73
    SequentialGroup
    0.60
    /*
    0.58
     дописавши
    0.58
    //
    0.58
    ANSA
    0.58
    ########.
    0.56
    osto
    0.54
     Mazz
    0.53
     nonatomic
    0.52
    Activations Density 0.028%

    No Known Activations