© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    identifiers related to system configuration and hardware components

    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
    RegressionTest
    -0.56
    Referències
    -0.56
     jsPsych
    -0.52
    lorette
    -0.52
     betweenstory
    -0.51
     shui
    -0.46
     LoggerFactory
    -0.46
    จึง
    -0.45
    ۖ
    -0.44
     enca
    -0.44
    POSITIVE LOGITS
    arResult
    0.82
    +:+
    0.75
    MAXN
    0.70
    []
    0.68
    featureID
    0.65
    ficulty
    0.65
    OGND
    0.64
     FetchType
    0.64
    KEYCODE
    0.64
    fficients
    0.63
    Activations Density 0.266%

    No Known Activations