© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23825
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially in the context of statistical data or research findings

    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
    IsContent
    -0.66
    DispatchToProps
    -0.63
    下载附件
    -0.61
    FXMLLoader
    -0.60
     EClass
    -0.60
    AndroidJUnit
    -0.59
    Hozzáférés
    -0.59
    庁
    -0.58
    RegressionTest
    -0.58
    ########.
    -0.58
    POSITIVE LOGITS
     CURIAM
    0.75
    ImageContext
    0.59
    awtextra
    0.53
    InputModule
    0.53
    annica
    0.53
     TextAppearance
    0.53
     torchvision
    0.52
    ритори
    0.50
     banking
    0.50
    UTERS
    0.49
    Activations Density 0.014%

    No Known Activations