© 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. 26941
    Prev
    Next
    INDEX
    Explanations

    questions that express skepticism or challenge assumptions

    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
     surla
    -0.57
    consulté
    -0.54
     dropping
    -0.52
     שוליים
    -0.52
    GOTREF
    -0.52
    quê
    -0.50
     становника
    -0.50
     verme
    -0.48
     '\\;'
    -0.47
     Shining
    -0.47
    POSITIVE LOGITS
     Chwiliwch
    0.63
    roides
    0.59
    +#+#
    0.57
    SaveChangesAsync
    0.56
    GEBURTSDATUM
    0.53
    PreferredItem
    0.53
    diffuse
    0.53
     Penn
    0.52
    RequestBuilder
    0.51
     AssemblyCulture
    0.50
    Activations Density 0.055%

    No Known Activations