Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14250
    Prev
    Next
    INDEX
    Explanations

    pattern of vertical bar symbols indicating hierarchical or structural information

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     |
    -0.78
     $|\
    -0.73
    enumi
    -0.64
    }|\
    -0.61
     |\
    -0.61
     sanoo
    -0.60
    didSet
    -0.59
    glises
    -0.57
    الإنجليزية
    -0.54
    rrggbb
    -0.54
    POSITIVE LOGITS
    \|
    1.11
    __':
    
    0.73
    GEBURTS
    0.70
    \|^{
    0.68
     oprot
    0.68
    Vert
    0.68
     QtCore
    0.66
     unknownFields
    0.66
    \|\
    0.63
    '){
    
    0.63
    Activations Density 0.011%

    No Known Activations