© 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. 853
    Prev
    Next
    INDEX
    Explanations

    the word "instance" and code related words and functions

    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
    ⓘ
    -0.84
     Betts
    -0.84
     TextInputType
    -0.84
    CURLOPT
    -0.81
     Hartmann
    -0.81
    ignty
    -0.78
     StatefulWidget
    -0.77
     regata
    -0.77
     ARXIV
    -0.77
     NgModule
    -0.76
    POSITIVE LOGITS
     instance
    1.77
     Instance
    1.73
    Instance
    1.69
    instance
    1.69
    instances
    1.66
    Instances
    1.59
     instances
    1.58
     Instances
    1.55
     INSTANCE
    1.38
    INSTANCE
    1.28
    Activations Density 0.241%

    No Known Activations