© 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. 26044
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and relationships involving dimensions

    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
    InputBorder
    -0.68
    AndEndTag
    -0.57
    ScopeManager
    -0.55
    lalu
    -0.55
    pielen
    -0.51
     sved
    -0.48
     enough
    -0.48
     WaitForSeconds
    -0.47
    Hic
    -0.47
    Rourke
    -0.46
    POSITIVE LOGITS
    -​
    0.71
    ViewInit
    0.68
    Kjelder
    0.67
     saites
    0.63
    Erreferentziak
    0.63
    তথ্যসূত্র
    0.62
     للمعارف
    0.60
    -------
    0.56
     Мексичка
    0.56
    ⁃
    0.56
    Activations Density 0.017%

    No Known Activations