© 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. 25704
    Prev
    Next
    INDEX
    Explanations

    references to repetitive genetic elements and techniques related to insertion or integration of transposons

    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
     PyTuple
    -0.82
    TintMode
    -0.77
    rrggbb
    -0.68
    esModule
    -0.66
    LabelTagHelper
    -0.65
    RegistryLite
    -0.65
    KommentareTeilen
    -0.65
     Rasp
    -0.65
    OGND
    -0.63
    WEBPACK
    -0.61
    POSITIVE LOGITS
    甸
    0.53
     vuitton
    0.50
    EMPO
    0.50
    хо
    0.49
     enca
    0.49
    amon
    0.49
    воз
    0.48
    рма
    0.48
    stamos
    0.47
    gai
    0.46
    Activations Density 0.015%

    No Known Activations