© 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. 57
    Prev
    Next
    INDEX
    Explanations

    code elements such as variable names, API calls, and language keywords

    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
    </b>
    -0.68
    </u>
    -0.64
    ()));
    -0.63
    </strong>
    -0.61
    ))[
    -0.57
     
    -0.57
    IUrlHelper
    -0.56
    ThemeOverlay
    -0.55
    ()]);
    -0.54
    ())),
    -0.54
    POSITIVE LOGITS
    mybatisplus
    0.91
     MonoBehaviour
    0.87
     houſe
    0.82
    consulté
    0.81
     purpoſe
    0.80
    Παραπομπές
    0.75
     useHistory
    0.75
    ImageContext
    0.74
     ſtate
    0.71
     ſch
    0.71
    Activations Density 4.597%

    No Known Activations