© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1363
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, especially variables and symbols within dollar signs, in formulas

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     map
    -0.46
     null
    -0.46
    Contactez
    -0.45
    WriteTagHelper
    -0.45
    чай
    -0.45
     pat
    -0.42
     mapping
    -0.42
    GeneratedCode
    -0.41
     regular
    -0.41
    ToAction
    -0.41
    POSITIVE LOGITS
    ftagPool
    0.81
    IntoConstraints
    0.79
     referenties
    0.77
     onCreateView
    0.76
    MigrationBuilder
    0.73
     otomatig
    0.72
     ujednoznacz
    0.70
     ModelExpression
    0.68
    #+#
    0.66
    Autoritní
    0.65
    Activations Density 0.578%

    No Known Activations