© 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. 12774
    Prev
    Next
    INDEX
    Explanations

    questions that express curiosity or seek clarification

    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
     reasons
    -0.73
    หวัด
    -0.69
     reason
    -0.69
     raisons
    -0.67
     excuses
    -0.65
     przyczyn
    -0.64
     alasan
    -0.63
    سبب
    -0.63
    reasons
    -0.63
     Reasons
    -0.62
    POSITIVE LOGITS
    QMetaType
    0.68
    antium
    0.67
    rungsseite
    0.66
    对自己
    0.65
    fony
    0.64
     Thirdly
    0.63
     ViewPager
    0.62
    contre
    0.61
    ONOMY
    0.61
    eezy
    0.60
    Activations Density 0.015%

    No Known Activations