© 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. 22867
    Prev
    Next
    INDEX
    Explanations

    phrases representing varying levels of emotional or sensory experiences

    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
    Not in Any Lists

    No Comments

    Negative Logits
    invokeLater
    -0.69
     resourceCulture
    -0.62
    Rüyada
    -0.56
    keyColumn
    -0.56
    adpleegd
    -0.54
    oOo
    -0.54
    Filmographie
    -0.54
    NamedQueries
    -0.54
    oa̍t
    -0.53
     mostrarán
    -0.53
    POSITIVE LOGITS
     NDEBUG
    0.57
     BoxFit
    0.55
     Trist
    0.54
     Corne
    0.50
    tidaknya
    0.49
     sympy
    0.48
    acyjny
    0.47
     MatDialog
    0.47
     unimagin
    0.47
     مرئيه
    0.47
    Activations Density 0.003%

    No Known Activations