© 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. 23676
    Prev
    Next
    INDEX
    Explanations

    the negation of statements or concepts

    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
    Personensuche
    -1.15
    expandindo
    -1.09
    ViewFeatures
    -1.05
    jsii
    -1.02
     '\\;'
    -1.00
     ModelExpression
    -0.99
    ⓧ
    -0.98
     kasarigan
    -0.97
    MessageTagHelper
    -0.93
    #![
    -0.92
    POSITIVE LOGITS
     kann
    0.63
    väg
    0.60
     can
    0.56
     puede
    0.56
    біль
    0.55
     might
    0.54
     saja
    0.54
     bornes
    0.54
     may
    0.52
     عد
    0.52
    Activations Density 0.066%

    No Known Activations