© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5064
    Prev
    Next
    INDEX
    Explanations

    discussions related to ethical dilemmas and motivations in human behavior

    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
     AssemblyCulture
    -0.89
    ContentAsync
    -0.82
     disambiguazione
    -0.77
     виправивши
    -0.76
    SourceChecksum
    -0.75
    matchCondition
    -0.69
    SizeMode
    -0.69
    expandindo
    -0.68
     للمعارف
    -0.65
    ValueStyle
    -0.64
    POSITIVE LOGITS
     reasons
    0.69
     REASONS
    0.68
    REASONS
    0.67
    reasons
    0.67
     Reasons
    0.64
    Reasons
    0.60
     motives
    0.56
     wanting
    0.56
     motivi
    0.56
     purpose
    0.54
    Activations Density 0.784%

    No Known Activations