© 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. 20592
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic funding and fellowships

    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
    NgModule
    -0.45
     Wyman
    -0.45
    رن
    -0.44
    AttributeValue
    -0.44
    ichten
    -0.43
     industriale
    -0.43
     Relevance
    -0.42
     molle
    -0.42
     LIABLE
    -0.42
     chives
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.99
    ="@+
    0.75
    ngdoc
    0.75
    gatsby
    0.72
    hoeddwyd
    0.68
     getItemId
    0.68
    Leod
    0.65
    isnan
    0.65
    AddTagHelper
    0.64
     disambiguazione
    0.63
    Activations Density 0.017%

    No Known Activations