© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    code-related operations or functions involving time, numbers, or age attributes

    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
    verwijspagina
    -0.89
     ComVisible
    -0.83
    RectangleBorder
    -0.81
    bewerken
    -0.68
    setVerticalGroup
    -0.66
    цездатний
    -0.65
     Мексичка
    -0.64
    expandindo
    -0.64
    ColumnHeaders
    -0.63
     AssemblyCompany
    -0.63
    POSITIVE LOGITS
     Removed
    0.49
    Filmografie
    0.49
    typeof
    0.45
    Removed
    0.44
     action
    0.44
     firmar
    0.44
     Eing
    0.43
    Diwedd
    0.43
    NUMX
    0.43
    wix
    0.42
    Activations Density 0.174%

    No Known Activations