© 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. 0-RES-MATRYOSHKA-DC
    7. 12541
    Prev
    Next
    INDEX
    Explanations

    landmarks and important milestones

    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
    GraphicsUnit
    -0.77
    sizeCache
    -0.59
    parsedMessage
    -0.57
     Harbor
    -0.56
    FetchType
    -0.55
    èdia
    -0.54
    RAINT
    -0.53
    iorno
    -0.52
    Trie
    -0.51
    bootstrapcdn
    -0.50
    POSITIVE LOGITS
     landmark
    1.42
     landmarks
    1.21
    landmark
    1.08
     milestone
    1.03
    Landmark
    1.03
     Landmark
    1.00
     Milestone
    0.96
     Landmarks
    0.95
    Milestone
    0.89
     milestones
    0.89
    Activations Density 0.003%

    No Known Activations