© 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. 17436
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to theories and models in physics

    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
    PreferredItem
    -0.81
     Италијани
    -0.79
    pushFollow
    -0.77
    MLLoader
    -0.75
    tagHelperRunner
    -0.71
    
    -0.67
     continuant
    -0.67
    Демографія
    -0.65
    fjspx
    -0.65
    SharedDtor
    -0.63
    POSITIVE LOGITS
    stående
    0.52
     Jan
    0.45
     virtual
    0.45
    юрпри
    0.45
    reactstrap
    0.43
     key
    0.43
    encial
    0.43
     simulation
    0.43
     nhấn
    0.42
    QPalette
    0.42
    Activations Density 0.267%

    No Known Activations