© 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. 29840
    Prev
    Next
    INDEX
    Explanations

    terms related to ignorance or the act of ignoring

    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
    pital
    -0.77
    principalColumn
    -0.76
     McKay
    -0.68
    INCREF
    -0.67
    skip
    -0.65
    ########.
    -0.65
     EconPapers
    -0.65
    Skip
    -0.64
    ंदीखरीदारी
    -0.63
     appContext
    -0.63
    POSITIVE LOGITS
     IGN
    1.16
     Ignorance
    1.02
     Ign
    0.98
     Vign
    0.98
     ignorance
    0.93
     Ignacio
    0.91
    Ign
    0.90
     Majefty
    0.90
     myſelf
    0.88
    ign
    0.87
    Activations Density 0.013%

    No Known Activations