© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical and chemical 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
     يتيمه
    -0.87
    ftagPool
    -0.80
    EDEFAULT
    -0.77
     Alk
    -0.73
    󠁴
    -0.72
    ipedia
    -0.72
     كومونز
    -0.71
    تقاوى
    -0.71
    Datuak
    -0.69
    TabStop
    -0.68
    POSITIVE LOGITS
    Diweddarwch
    0.50
    selectAll
    0.48
    Dimethyl
    0.48
    }],
    0.47
     conse
    0.47
    Tril
    0.47
    addGap
    0.46
    뭉
    0.46
     düşünü
    0.42
     dimethyl
    0.42
    Activations Density 0.030%

    No Known Activations