© 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. 16866
    Prev
    Next
    INDEX
    Explanations

    questions indicating surprise or disbelief

    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
    Negative Logits
     Protección
    -0.48
     TPS
    -0.47
     braccia
    -0.47
    noks
    -0.46
    lorette
    -0.45
    atég
    -0.43
     silicona
    -0.43
     BitmapFactory
    -0.43
     Ropa
    -0.43
    ImageContext
    -0.43
    POSITIVE LOGITS
    AutoField
    0.69
    VersionUID
    0.68
    fjspx
    0.61
    Kariera
    0.59
    原始内容存档于
    0.56
    homonymie
    0.55
    elang
    0.55
    χο
    0.53
    rungsseite
    0.52
    Referencie
    0.52
    Activations Density 0.012%

    No Known Activations