© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8841
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics presented in percentage form

    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
    )";
    -0.85
     defaultstate
    -0.74
    IsContent
    -0.73
    DoubleQuotes
    -0.73
     Himo
    -0.71
    <tfoot>
    -0.70
    ISupport
    -0.69
    RefNanny
    -0.69
    Diweddarwch
    -0.69
    ContentAsync
    -0.67
    POSITIVE LOGITS
    reactstrap
    0.64
    itza
    0.42
     pet
    0.41
     الصورة
    0.41
    Strut
    0.40
     ชิ้น
    0.40
    VEHICLE
    0.38
    Narrative
    0.38
    収録曲
    0.38
    ruce
    0.38
    Activations Density 0.030%

    No Known Activations