© 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. 9315
    Prev
    Next
    INDEX
    Explanations

    numeric data associated with input and output in a training context

    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
    Personendaten
    -0.88
     Administrativna
    -0.79
    WithIOException
    -0.79
    principalColumn
    -0.78
     disambiguazione
    -0.76
    IndentedString
    -0.75
    SequentialGroup
    -0.74
    Personensuche
    -0.71
    principalTable
    -0.71
    msgTypes
    -0.71
    POSITIVE LOGITS
    odal
    0.56
    giat
    0.52
    cheme
    0.51
     conocen
    0.50
    gia
    0.48
     Tennant
    0.47
     recette
    0.46
    ranes
    0.45
     praça
    0.44
    morphism
    0.44
    Activations Density 0.006%

    No Known Activations