© 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. 32217
    Prev
    Next
    INDEX
    Explanations

    references to 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
    TagMode
    -0.69
    ंदीखरीदारी
    -0.63
     charité
    -0.63
     myſelf
    -0.59
    MinWidth
    -0.58
    FormTagHelper
    -0.58
     épreuve
    -0.58
    iança
    -0.56
    AnchorStyles
    -0.56
     roulant
    -0.55
    POSITIVE LOGITS
    andExpect
    0.64
     autorytatywna
    0.63
     ComVisible
    0.62
    قایناقلار
    0.61
    Autoritní
    0.60
     beginnetje
    0.58
    yeezy
    0.55
     createState
    0.55
    thenReturn
    0.54
     ')
    0.54
    Activations Density 0.097%

    No Known Activations