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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30176
    Prev
    Next
    INDEX
    Explanations

    words related to wisdom and knowledge

    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
    外部リンク
    -0.69
     ویکی‌پدی
    -0.67
    ########.
    -0.67
    teilung
    -0.66
    AccessorTable
    -0.66
    Примітки
    -0.65
    ьаж
    -0.65
     Chamb
    -0.64
    rophilic
    -0.62
    laund
    -0.62
    POSITIVE LOGITS
     Wiseman
    1.18
     Wisdom
    1.15
     wisdom
    1.09
     Wise
    1.08
    Wisdom
    1.05
     Wis
    1.04
     wise
    1.02
     WISE
    1.00
     WIS
    0.98
     SAGE
    0.93
    Activations Density 0.005%

    No Known Activations