© 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. 21124
    Prev
    Next
    INDEX
    Explanations

    references to desired or undesired attributes of technologies and their compatibility

    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
    Negative Logits
     ri
    -0.44
     pour
    -0.40
     super
    -0.40
     di
    -0.39
     (
    -0.38
     pau
    -0.38
     van
    -0.37
    setAttribute
    -0.37
     su
    -0.37
     sa
    -0.37
    POSITIVE LOGITS
     مشين
    1.09
    tagHelperRunner
    1.04
     متعلقه
    0.88
    TagHelper
    0.87
    ftagPool
    0.86
    ParallelGroup
    0.81
    adaptiveStyles
    0.81
    tagext
    0.81
    esModule
    0.81
    GenerationType
    0.80
    Activations Density 0.197%

    No Known Activations