© 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. 12-RES-MATRYOSHKA-DC
    7. 5736
    Prev
    Next
    INDEX
    Explanations

    concepts related to comprehension and awareness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    الثة
    -0.66
    NOTIFY
    -0.66
     urbanas
    -0.65
     frattempo
    -0.65
     colpo
    -0.64
    φυ
    -0.63
     Pohl
    -0.61
     Nax
    -0.60
     Avic
    -0.60
     voltaje
    -0.60
    POSITIVE LOGITS
    understood
    1.12
     Understand
    1.09
    Understand
    1.09
    understand
    1.08
     understandable
    1.05
     understood
    1.01
     understand
    0.96
     understanding
    0.92
     understands
    0.92
     begrij
    0.90
    Activations Density 0.048%

    No Known Activations