© 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. 12-RES-MATRYOSHKA-DC
    7. 2007
    Prev
    Next
    INDEX
    Explanations

    reference to medical conditions and their prevalence or statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.65
     propOrder
    -0.63
    DECREF
    -0.60
     mitotic
    -0.57
     reír
    -0.57
     ControllerBase
    -0.57
    retario
    -0.56
     Buxton
    -0.56
     MainAxisSize
    -0.56
     ioutil
    -0.55
    POSITIVE LOGITS
    -------
    0.53
    aarrggbb
    0.51
    RTLD
    0.50
    UnusedPrivate
    0.50
    Quer
    0.50
    AndroidJUnit
    0.49
    onames
    0.48
    <bos>
    0.47
    sizeCache
    0.47
    зня
    0.46
    Activations Density 0.226%

    No Known Activations