© 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. 22725
    Prev
    Next
    INDEX
    Explanations

    terms related to technical descriptions and coding snippets

    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
    msgSender
    -0.44
     caveats
    -0.44
    bobox
    -0.41
     winners
    -0.40
    solicited
    -0.40
    gonic
    -0.39
    ,:),
    -0.39
     getApp
    -0.39
    routeProvider
    -0.39
    bukkit
    -0.38
    POSITIVE LOGITS
     sección
    0.73
     section
    0.73
     étape
    0.72
     esternos
    0.71
     Sección
    0.70
     seção
    0.69
    sphase
    0.68
    awtextra
    0.68
    adil
    0.66
     sezione
    0.66
    Activations Density 0.793%

    No Known Activations