© 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. 15577
    Prev
    Next
    INDEX
    Explanations

    words related to emulsification and emulsions in various 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
    PreferredItem
    -1.09
    theless
    -0.94
     RTI
    -0.92
     Roch
    -0.91
     ddelweddau
    -0.90
    anasia
    -0.87
     Roscoe
    -0.87
     Wolfram
    -0.85
     Axiom
    -0.85
    messageInfo
    -0.84
    POSITIVE LOGITS
     Em
    1.34
     em
    1.13
    Em
    1.10
    EM
    1.05
     EM
    1.04
    </em>
    0.98
    em
    0.95
     Emory
    0.90
     Emmer
    0.89
     emulsions
    0.85
    Activations Density 0.064%

    No Known Activations