© 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. 13649
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "exist" and variations of the word "well."

    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
     AssemblyCulture
    -0.86
     idéia
    -0.84
     idée
    -0.81
     Edin
    -0.81
     يتيمه
    -0.79
     idea
    -0.77
    extAlignment
    -0.77
    Personendaten
    -0.75
     IDEA
    -0.73
     partid
    -0.70
    POSITIVE LOGITS
    
    1.21
    velte
    0.63
    Devo
    0.61
    oldown
    0.60
    ukary
    0.60
    *****
    0.59
    τερα
    0.59
     Devo
    0.59
    ViewChild
    0.59
    anoma
    0.58
    Activations Density 0.000%

    No Known Activations