© 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. 26125
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to recommendations and personal preferences in products or services

    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
     autorytatywna
    -0.61
     unknownFields
    -0.54
    @[+][
    -0.52
    arXiv
    -0.50
    setupUi
    -0.50
    Legături
    -0.48
    NavController
    -0.47
    dden
    -0.47
    первых
    -0.46
    WebElementEntity
    -0.46
    POSITIVE LOGITS
     Factbook
    0.61
    IUrlHelper
    0.56
    >--}}
    0.56
    NUMX
    0.54
    tvguidetime
    0.54
    ()")
    0.52
    endphp
    0.50
    elry
    0.49
    +")
    0.49
    =$?
    0.49
    Activations Density 0.270%

    No Known Activations