© 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. 30606
    Prev
    Next
    INDEX
    Explanations

    expressions of personal struggles and emotional distress

    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
    Hentet
    -0.68
     confronti
    -0.64
    chyma
    -0.60
    TargetApi
    -0.57
     actuelles
    -0.56
     endfor
    -0.55
    opheles
    -0.55
     Reuter
    -0.54
    ijão
    -0.53
    了吧
    -0.52
    POSITIVE LOGITS
    Wasn
    0.84
    ıyordu
    0.83
     Wasn
    0.78
    acakt
    0.78
     wasn
    0.76
    wasn
    0.72
    DoubleQuotes
    0.69
     was
    0.69
     hadn
    0.69
    CPtr
    0.67
    Activations Density 0.227%

    No Known Activations