© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1177
    Prev
    Next
    INDEX
    Explanations

    equations and numerical relationships, including the words "solve", "calculate", "what is the value of", and question marks at the end of lines.

    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.22.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.22.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
    neſs
    -0.90
    ſelf
    -0.88
    ſelves
    -0.84
    \<^
    -0.84
    */;
    -0.84
    niająca
    -0.79
    >\<^
    -0.77
    nefs
    -0.77
     ་་
    -0.73
     }}$}
    -0.70
    POSITIVE LOGITS
     représent
    0.59
     Which
    0.53
    ↵
    0.52
    Magenta
    0.52
     =
    0.51
    x
    0.51
     representar
    0.50
    then
    0.49
     domestiques
    0.49
     Mein
    0.48
    Activations Density 4.143%

    No Known Activations