© 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. 6431
    Prev
    Next
    INDEX
    Explanations

    segments of text containing specific Croatian words related to "at," "attack," "privacy," or "security."

    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
    gående
    -0.57
    ')}}
    -0.54
    ]<<"
    -0.52
    "}\
    -0.48
    //}
    -0.48
    ']
    -0.47
    "]
    -0.47
    ']))
    -0.46
    '],
    -0.46
    }^{*}\
    -0.46
    POSITIVE LOGITS
    enumii
    0.85
    AccessorTable
    0.80
    ings
    0.79
    ishment
    0.77
    تقاوى
    0.71
    NameInMap
    0.69
    INGS
    0.69
    ishments
    0.68
    XmlSchema
    0.68
    nings
    0.68
    Activations Density 0.236%

    No Known Activations