© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 339
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations within a formal context

    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
    fjspx
    -1.05
    StoryboardSegue
    -1.01
    antMatchers
    -0.99
     propOrder
    -0.97
     tombé
    -0.96
    findpost
    -0.96
     définiti
    -0.96
     renforcé
    -0.95
     femininas
    -0.95
     refroid
    -0.94
    POSITIVE LOGITS
    {{\
    0.74
    {\
    0.71
     {\
    0.67
    mathbf
    0.67
    {
    0.66
    rm
    0.66
    textbf
    0.63
    mathfrak
    0.60
    {{
    0.60
    ={\
    0.59
    Activations Density 1.464%

    No Known Activations