© 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. 23877
    Prev
    Next
    INDEX
    Explanations

    references to specific types of compounds or methodologies in scientific contexts

    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
     Lich
    -0.73
     Lennon
    -0.71
     nant
    -0.69
    nino
    -0.69
    nol
    -0.68
    nthetic
    -0.67
     Sump
    -0.66
    nition
    -0.66
    ubility
    -0.66
     Bisch
    -0.66
    POSITIVE LOGITS
     Sykes
    1.29
     Sy
    1.27
    Sy
    1.26
    sy
    1.15
     sy
    1.13
     Sycamore
    0.99
     Syed
    0.89
    جوايز
    0.84
     SY
    0.77
     syphilis
    0.76
    Activations Density 0.006%

    No Known Activations