© 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. 22-RES-MATRYOSHKA-DC
    7. 3207
    Prev
    Next
    INDEX
    Explanations

    the words "above" and "below"

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    PropertyChanging
    -0.71
    --)
    -0.65
    orianCalendar
    -0.61
    ')")
    -0.61
    VolleyError
    -0.57
     resultCode
    -0.57
    DrawerToggle
    -0.56
     >=",
    -0.55
     SqlConnection
    -0.54
    stonia
    -0.54
    POSITIVE LOGITS
    mentioned
    1.46
    ground
    1.05
     mentioned
    1.03
     Mentioned
    0.85
    👆
    0.70
     ground
    0.70
    ABOVE
    0.69
    GROUND
    0.69
     ExecuteAsync
    0.68
     mencion
    0.67
    Activations Density 0.063%

    No Known Activations