© 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. 18-RES-MATRYOSHKA-DC
    7. 892
    Prev
    Next
    INDEX
    Explanations

    the word "old" and relative terms like "younger"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     Ressources
    -0.81
     سكانية
    -0.79
     createSprite
    -0.75
    esgue
    -0.72
    Personensuche
    -0.72
    eroy
    -0.70
    ViewFeatures
    -0.69
    amaño
    -0.68
    createCanvas
    -0.67
     mxArray
    -0.66
    POSITIVE LOGITS
     fashioned
    1.16
    fashioned
    0.90
     Old
    0.76
    Old
    0.75
     OLD
    0.73
     доб
    0.64
    old
    0.63
     old
    0.63
     vieux
    0.63
     outdated
    0.62
    Activations Density 0.345%

    No Known Activations