© 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. 26589
    Prev
    Next
    INDEX
    Explanations

    references to dialysis

    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
     propOrder
    -0.92
    AndEndTag
    -0.87
     ostavi
    -0.85
    MethodManager
    -0.83
    arakhand
    -0.80
     للمعارف
    -0.80
    تقاوى
    -0.79
    ImageContext
    -0.77
    Diwedd
    -0.75
     XCTest
    -0.71
    POSITIVE LOGITS
     dial
    1.31
     dialysis
    1.30
     Dial
    1.28
    alysis
    1.16
    Dial
    1.16
     DIAL
    1.08
    dial
    1.01
     dials
    0.86
     dialec
    0.84
    Dialect
    0.79
    Activations Density 0.002%

    No Known Activations