© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10317
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities in comparison contexts

    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
    writeFieldEnd
    -0.65
     useCallback
    -0.57
    žová
    -0.55
     InputDecoration
    -0.52
    ElementException
    -0.52
     ostavi
    -0.51
    setters
    -0.51
    Direction
    -0.50
    bugs
    -0.50
    liet
    -0.49
    POSITIVE LOGITS
     knex
    0.51
     Grecs
    0.51
     Pristupljeno
    0.48
    Expedia
    0.48
    اں
    0.47
    atamente
    0.47
    ebenarnya
    0.46
    ungkinan
    0.45
    otheby
    0.45
    ArgsConstructor
    0.45
    Activations Density 0.108%

    No Known Activations