© 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. 22881
    Prev
    Next
    INDEX
    Explanations

    conversational expressions related to uncertainty and introspection

    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
    :✨
    -0.60
     counterfeit
    -0.55
    intéress
    -0.54
    BlockPos
    -0.54
     facie
    -0.54
     itſelf
    -0.54
    FXML
    -0.53
    ifflin
    -0.51
     invokevirtual
    -0.51
    shadowRadius
    -0.51
    POSITIVE LOGITS
    <bos>
    0.82
    GraphicsUnit
    0.74
     AssemblyTitle
    0.62
    ".$_
    0.57
    styleUrls
    0.56
    webElementXpaths
    0.54
     fordi
    0.53
     Because
    0.52
     disesuaikan
    0.51
     eftersom
    0.50
    Activations Density 0.147%

    No Known Activations