© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    elements related to structures and components typically used in music and academic or organizational contexts

    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
    DataAnnotations
    -0.61
    Espèce
    -0.52
    specialchars
    -0.52
    Gruss
    -0.51
     petal
    -0.47
    dafx
    -0.47
    pagos
    -0.47
    навли
    -0.46
    Насе
    -0.44
    zież
    -0.43
    POSITIVE LOGITS
     ویکی‌پدی
    0.72
    SourceChecksum
    0.71
     CreateTagHelper
    0.68
    RegressionTest
    0.68
    ///</
    0.65
    MigrationBuilder
    0.64
    UnusedPrivate
    0.63
     iprot
    0.61
    ***************/
    0.60
     متعلقه
    0.60
    Activations Density 1.259%

    No Known Activations