© 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. 23806
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to currency formats

    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
    parsedMessage
    -0.88
    UnusedPrivate
    -0.88
     estimés
    -0.83
    InvalidProtocol
    -0.79
    ViewFeatures
    -0.77
     ModelExpression
    -0.77
    AddTagHelper
    -0.76
    msgTypes
    -0.75
    الحياه
    -0.71
    MessageTagHelper
    -0.69
    POSITIVE LOGITS
     postale
    0.59
     toepassing
    0.58
    ainte
    0.57
     Tully
    0.52
     Edy
    0.52
    colore
    0.51
     skolan
    0.50
    ябре
    0.49
     maît
    0.49
    laget
    0.48
    Activations Density 0.004%

    No Known Activations