© 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. 20023
    Prev
    Next
    INDEX
    Explanations

    phrases conveying contrasting or contradictory information

    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
    setopt
    -0.48
    fordern
    -0.47
     onPostExecute
    -0.45
    emu
    -0.43
     future
    -0.41
    valier
    -0.41
    DotNetBar
    -0.41
    lamy
    -0.41
    microb
    -0.40
    ethers
    -0.40
    POSITIVE LOGITS
     Paglinawan
    1.05
     Wicidata
    0.77
    DoubleQuotes
    0.77
     Réponses
    0.72
    исленность
    0.71
     незавершена
    0.67
     pourtant
    0.63
    ftagPool
    0.62
    ViewImports
    0.61
    DockStyle
    0.60
    Activations Density 0.104%

    No Known Activations