© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 323
    Prev
    Next
    INDEX
    Explanations

    chemical terminology, specifically focusing on chemical structures and interactions related to phenolic compounds

    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
    <eos>
    -1.00
     
    -0.69
    ValueStyle
    -0.66
     "
    -0.63
    )))),
    -0.59
    expandindo
    -0.58
     “
    -0.58
    ↵↵↵
    -0.56
    ]){
    -0.54
    <b>
    -0.54
    POSITIVE LOGITS
    </strong>
    1.25
    </em>
    1.09
    </u>
    1.06
    </b>
    1.02
    </code>
    0.96
    ”…
    0.96
    ”!
    0.95
     itſelf
    0.91
    </h2>
    0.89
    ”
    0.89
    Activations Density 5.887%

    No Known Activations