© 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. 14211
    Prev
    Next
    INDEX
    Explanations

    terms related to laboratory equipment and products

    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
    <eos>
    -0.61
    UA
    -0.40
     liquid
    -0.40
    Authorization
    -0.38
    IGI
    -0.38
     authorization
    -0.37
     Ly
    -0.36
    na
    -0.36
    usse
    -0.36
    webp
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    1.06
     CreateTagHelper
    0.95
     <<<<<<<<<<<<<<
    0.95
     unknownFields
    0.90
     calendriers
    0.89
     '\\;'
    0.88
     &___
    0.83
     متحده
    0.82
    RegressionTest
    0.82
     Савезне
    0.81
    Activations Density 0.214%

    No Known Activations