© 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. 24-RES-MATRYOSHKA-DC
    7. 431
    Prev
    Next
    INDEX
    Explanations

    mathematical and physics notation

    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.24.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.24.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
     kasarigan
    -0.74
    المشاركات
    -0.70
     بيها
    -0.67
     NSCoder
    -0.65
    AsUp
    -0.64
    ఔ
    -0.63
     onOptions
    -0.61
    олові
    -0.59
    HasAnnotation
    -0.58
     <>",
    -0.58
    POSITIVE LOGITS
     \
    1.31
     $\
    1.30
    \
    1.17
    $\
    0.99
    ="\
    0.94
    '\
    0.88
     "\
    0.86
    {\
    0.84
    <<"\
    0.81
    $$\
    0.79
    Activations Density 3.486%

    No Known Activations