© 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. 26009
    Prev
    Next
    INDEX
    Explanations

    terms associated with funding and support for academic and medical research activities

    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
     saites
    -0.75
     Visitors
    -0.64
    glieder
    -0.59
    Visitors
    -0.59
     visitors
    -0.59
    Roc
    -0.53
     visitor
    -0.52
     bénévoles
    -0.52
     constitution
    -0.52
    oderm
    -0.51
    POSITIVE LOGITS
    CppCodeGen
    0.64
    posedge
    0.62
    StoryboardSegue
    0.61
    djangoproject
    0.56
    IsMutable
    0.56
    writeField
    0.56
     needy
    0.54
    GraphicsUnit
    0.53
    TagMode
    0.53
    RefNanny
    0.53
    Activations Density 0.105%

    No Known Activations