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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15321
    Prev
    Next
    INDEX
    Explanations

    expressions of ideas or concepts related to generating or sharing ideas

    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
    principles
    -1.27
     principles
    -1.26
     Principles
    -1.25
    Principles
    -1.19
     PRINCIPLES
    -1.06
     فريبيس
    -0.95
     createSprite
    -0.87
    Diwedd
    -0.86
    FieldNumber
    -0.80
     للمعارف
    -0.78
    POSITIVE LOGITS
     principal
    0.98
     Principal
    0.89
    Principal
    0.87
    principal
    0.84
     ideas
    0.83
     PRINCIPAL
    0.71
    cipal
    0.68
    ideas
    0.68
     Ideas
    0.62
     chief
    0.60
    Activations Density 0.003%

    No Known Activations