© 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. 21196
    Prev
    Next
    INDEX
    Explanations

    terms associated with biochemical extraction and purification processes

    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
     doubtnut
    -0.84
     CHAPITRE
    -0.64
     محفوظة
    -0.63
    ^(@)
    -0.62
     /\.(
    -0.62
     itſelf
    -0.61
    ousands
    -0.60
    ברס
    -0.60
    intenant
    -0.59
     pagoda
    -0.59
    POSITIVE LOGITS
    цин
    0.44
    CreateModel
    0.44
     Walkover
    0.43
    #+#
    0.41
     GetEnumerator
    0.41
    Ex
    0.40
    equalsIgnoreCase
    0.40
     Ins
    0.40
     Lauf
    0.40
    给你
    0.40
    Activations Density 0.020%

    No Known Activations