© 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. 11980
    Prev
    Next
    INDEX
    Explanations

    terms related to weighted averages in statistical or mathematical contexts

    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
     Borel
    -0.72
    pearance
    -0.71
    Datuak
    -0.70
     Sakit
    -0.69
     useState
    -0.67
     defaultstate
    -0.67
     Crim
    -0.66
    intenance
    -0.65
     onCreateView
    -0.65
     Rainier
    -0.64
    POSITIVE LOGITS
     weighted
    0.78
    weighted
    0.71
    DoubleQuotes
    0.69
    {}".
    0.68
    Weighted
    0.68
     Weighted
    0.66
    {}'.
    0.62
     vyt
    0.57
     {},
    0.53
     {},
    0.53
    Activations Density 0.005%

    No Known Activations