© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 206
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and similar demonstrative references

    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
     betweenstory
    -1.01
    LookAnd
    -0.98
    writeFieldEnd
    -0.92
    httphttps
    -0.85
    InteropServices
    -0.81
     medusa
    -0.79
     Lukaku
    -0.79
     protoimpl
    -0.78
    NameInMap
    -0.77
     Protobuf
    -0.77
    POSITIVE LOGITS
     THIS
    1.20
    THIS
    1.13
    This
    1.09
     This
    1.04
    this
    1.03
     this
    1.00
     esta
    0.71
    Esta
    0.71
    Этот
    0.69
     ésta
    0.68
    Activations Density 1.445%

    No Known Activations