© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11275
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to functions and their properties

    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
    AndEndTag
    -0.89
     resourceCulture
    -0.70
    bewerken
    -0.59
     ***!
    -0.55
    LabelTagHelper
    -0.54
    tagHelper
    -0.50
     mith
    -0.50
    ảy
    -0.50
     donate
    -0.48
    invokeLater
    -0.48
    POSITIVE LOGITS
    braio
    0.63
    ionario
    0.60
     vänt
    0.54
    pflicht
    0.51
    FXML
    0.50
    кономи
    0.49
     đỡ
    0.49
    Sus
    0.49
    ้าน
    0.49
    seamnă
    0.49
    Activations Density 0.041%

    No Known Activations