© 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. 6132
    Prev
    Next
    INDEX
    Explanations

    sentences expressing personal opinions or sentiments

    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
    Negative Logits
     supuestamente
    -0.63
     reportedly
    -0.63
     supposedly
    -0.62
     apparently
    -0.60
    Apparently
    -0.60
     Apparently
    -0.58
     allegedly
    -0.55
    apparently
    -0.54
     P
    -0.54
    us
    -0.51
    POSITIVE LOGITS
    enumii
    1.07
     فريبيس
    1.05
    клопе
    0.99
     contextLoads
    0.95
    UserScript
    0.92
    featureID
    0.92
    EDEFAULT
    0.91
     NSCoder
    0.90
    principalColumn
    0.84
    WebElementEntity
    0.84
    Activations Density 0.544%

    No Known Activations