© 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. 21655
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and phrases related to treatment protocols and safety in clinical settings

    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
     незавершена
    -0.94
     Мексичка
    -0.88
     FetchType
    -0.88
    Tembelea
    -0.87
     ExecuteAsync
    -0.86
    NewUrlParser
    -0.85
    ItemBackground
    -0.83
     ModelExpression
    -0.82
    GraphicsUnit
    -0.82
    ValueGeneration
    -0.82
    POSITIVE LOGITS
    hled
    0.40
     maglia
    0.37
    ]();
    0.37
    M
    0.37
    zedł
    0.36
     zd
    0.36
    ce
    0.35
    Shouldn
    0.35
    ent
    0.35
     massiv
    0.34
    Activations Density 0.937%

    No Known Activations