© 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. 1-RES-MATRYOSHKA-DC
    7. 1551
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds, specifically 'acid' and 'ick'

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    lom
    -0.52
    Gweler
    -0.52
    CHAFT
    -0.52
    อนไลน์
    -0.51
     derer
    -0.51
     kasarigan
    -0.50
    Zem
    -0.50
     urme
    -0.50
    KindOfClass
    -0.49
     détach
    -0.49
    POSITIVE LOGITS
    msgid
    5.63
    AndEndTag
    0.99
    msgstr
    0.92
    messageId
    0.89
    getMsg
    0.88
     msg
    0.82
     messages
    0.71
     Messages
    0.70
    setMsg
    0.70
    MessageId
    0.70
    Activations Density 0.001%

    No Known Activations