© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 942
    Prev
    Next
    INDEX
    Explanations

    the word "public" or phrases containing the word "public"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.80
    AccessorTable
    -0.75
    memoized
    -0.73
    Hochspringen
    -0.67
    fromnode
    -0.63
    mergeFrom
    -0.63
    prime
    -0.63
    InjectAttribute
    -0.61
    Prime
    -0.60
     noastre
    -0.59
    POSITIVE LOGITS
     health
    0.81
     sector
    0.76
    health
    0.70
     domain
    0.69
    HEALTH
    0.67
    sector
    0.65
    ally
    0.65
     Health
    0.63
     Sector
    0.63
    spirited
    0.62
    Activations Density 0.095%

    No Known Activations