© 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. 23884
    Prev
    Next
    INDEX
    Explanations

    instances of consecutive occurrences, especially in medical studies

    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
     SEDS
    -0.67
    енча
    -0.67
    brushes
    -0.66
    ngths
    -0.65
    calar
    -0.63
    '},
    -0.60
    )}</
    -0.57
    cieli
    -0.57
    scha
    -0.57
     aidant
    -0.57
    POSITIVE LOGITS
    secutive
    0.98
     présidenti
    0.75
    igshid
    0.72
    +#+#
    0.71
     Katal
    0.71
    
    0.70
     médié
    0.69
     Compagn
    0.68
     Reſ
    0.68
     occaf
    0.67
    Activations Density 0.002%

    No Known Activations