© 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. 19343
    Prev
    Next
    INDEX
    Explanations

    the word "being" or variations of it, indicating focus on states of existence or action

    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
    Géographie
    -0.75
    protoc
    -0.69
     Tait
    -0.67
    fecture
    -0.65
     on
    -0.65
     BoxDecoration
    -0.64
     verdade
    -0.63
     MonoBehaviour
    -0.62
    zone
    -0.62
    XmlAccessorType
    -0.61
    POSITIVE LOGITS
    empêcher
    0.67
    vedra
    0.67
    ····
    0.65
     dovuto
    0.62
    lepiej
    0.62
    horabuena
    0.62
    pleaños
    0.62
     Egyes
    0.62
     facilité
    0.60
     Orrell
    0.60
    Activations Density 0.016%

    No Known Activations