© 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. 5783
    Prev
    Next
    INDEX
    Explanations

    variables and identifiers in programming syntax

    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
     myſelf
    -0.82
     himſelf
    -0.75
     themſelves
    -0.73
     viſ
    -0.73
     occaf
    -0.72
     iſt
    -0.71
     téléphonique
    -0.70
     Eſ
    -0.68
     uſed
    -0.68
     ſtate
    -0.67
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
     import
    0.57
    PYX
    0.56
     form
    0.55
     
    0.54
     of
    0.51
     in
    0.50
     part
    0.50
     often
    0.50
     v
    0.49
    Activations Density 0.250%

    No Known Activations