© 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. 16781
    Prev
    Next
    INDEX
    Explanations

    terms related to oxidation processes and their effects

    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
    ]!='
    -0.69
    verwijspagina
    -0.63
     Zjednoc
    -0.61
     Seem
    -0.61
     Pelham
    -0.60
     tetrachloride
    -0.60
    erry
    -0.59
    llus
    -0.59
    Occurrences
    -0.59
     phonon
    -0.59
    POSITIVE LOGITS
     oxid
    1.11
     oxidation
    1.02
     Oxidation
    0.99
     Oxid
    0.98
     OX
    0.98
     Ox
    0.96
     Oxide
    0.92
    oxid
    0.87
    Oxid
    0.87
     oxidized
    0.82
    Activations Density 0.011%

    No Known Activations