© 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. 9196
    Prev
    Next
    INDEX
    Explanations

    references to powerful personal experiences or emotional expressions

    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
     typelib
    -0.68
    ayuno
    -0.55
     initComponents
    -0.52
     himo
    -0.48
     paff
    -0.47
    gya
    -0.47
    ฉ
    -0.47
     protoimpl
    -0.46
     absurdo
    -0.45
     advice
    -0.45
    POSITIVE LOGITS
    Datuak
    0.80
     Meksiku
    0.69
     MessageBoxIcon
    0.69
    HostException
    0.64
    IUrlHelper
    0.63
    WithIOException
    0.59
    Geplaatst
    0.57
    naments
    0.56
    >>>>>>>
    0.56
     հղումներ
    0.56
    Activations Density 0.010%

    No Known Activations