© 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. 18-RES-MATRYOSHKA-DC
    7. 344
    Prev
    Next
    INDEX
    Explanations

    division symbols, especially between numbers, suggesting it's looking at fractions and equations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     above
    -0.58
    ци
    -0.55
     lain
    -0.52
     mahi
    -0.52
     more
    -0.51
     First
    -0.51
    istu
    -0.51
    ist
    -0.50
     indis
    -0.50
    above
    -0.49
    POSITIVE LOGITS
     متعلقه
    1.05
    UserScript
    0.98
    __*/
    0.93
     Paglinawan
    0.91
     Мексичка
    0.88
    IUrlHelper
    0.88
    makeConstraints
    0.86
    Jereo
    0.84
    InputBorder
    0.82
    ('/
    0.82
    Activations Density 0.723%

    No Known Activations