© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13419
    Prev
    Next
    INDEX
    Explanations

    references to the mass or masses of astronomical objects

    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
     Mass
    -0.79
    Mass
    -0.72
    mass
    -0.70
     InputDecoration
    -0.70
     fabrik
    -0.65
     المعيارى
    -0.65
     متعلقه
    -0.63
     mass
    -0.63
    tableFuture
    -0.63
    UNRELATED
    -0.63
    POSITIVE LOGITS
     masses
    2.38
    masses
    1.61
     Masses
    1.59
     masas
    0.70
     crowds
    0.69
     crowd
    0.69
     массы
    0.58
     Crowd
    0.55
     populace
    0.55
    ökk
    0.52
    Activations Density 0.001%

    No Known Activations