© 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. 1630
    Prev
    Next
    INDEX
    Explanations

    variables and parameters used in mathematical expressions or equations

    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
     initComponents
    -0.83
     GenerationType
    -0.79
     SEÑ
    -0.77
    GenerationType
    -0.76
     Kaka
    -0.76
     kaka
    -0.75
    Masa
    -0.73
    IBar
    -0.73
     Mombasa
    -0.73
     Morm
    -0.73
    POSITIVE LOGITS
     U
    0.99
    uuuu
    0.94
     u
    0.91
    uu
    0.91
    uuu
    0.91
    UUUU
    0.91
    UU
    0.90
     uu
    0.87
     uncin
    0.85
     UU
    0.85
    Activations Density 2.075%

    No Known Activations