© 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. 30190
    Prev
    Next
    INDEX
    Explanations

    significant differences in clinical characteristics

    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
    LayoutStyle
    -0.54
     returned
    -0.49
     liefer
    -0.46
    mode
    -0.43
     unic
    -0.42
     mode
    -0.42
     mask
    -0.42
     erschienen
    -0.40
    Base
    -0.40
    base
    -0.40
    POSITIVE LOGITS
    SharedDtor
    0.80
    OGND
    0.76
    mapStateToProps
    0.75
    帖最后由
    0.73
    InjectAttribute
    0.70
     оригіналу
    0.69
    WriteBarrier
    0.68
    TagHelper
    0.64
    unately
    0.62
     ExecuteAsync
    0.62
    Activations Density 0.144%

    No Known Activations