© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24919
    Prev
    Next
    INDEX
    Explanations

    the Greek letter "mu" commonly associated with statistical measures or parameters

    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
    Negative Logits
    ividual
    -0.90
    WriteTagHelper
    -0.85
     tartalomajánló
    -0.81
    CodeAttribute
    -0.75
     nakalista
    -0.75
    koff
    -0.71
     tangerang
    -0.70
    Lakes
    -0.69
    ThroughAttribute
    -0.68
     Lakeside
    -0.67
    POSITIVE LOGITS
     Murillo
    0.67
    Muon
    0.66
     mu
    0.66
     typename
    0.66
    Mu
    0.65
    \'
    0.62
    Muri
    0.62
     Mu
    0.60
     ?>">
    0.59
    ]]>
    0.59
    Activations Density 0.088%

    No Known Activations