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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    terms related to specific proteins and their interactions with viruses

    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
     виправивши
    -0.95
     pleaſure
    -0.88
     Monfieur
    -0.86
     themſelves
    -0.83
     Efq
    -0.83
     myſelf
    -0.81
     Theſe
    -0.81
     purpoſe
    -0.81
    олові
    -0.79
     houſe
    -0.78
    POSITIVE LOGITS
    mantec
    0.52
     Z
    0.51
    Gweler
    0.50
    AMAHA
    0.50
     Clark
    0.49
     Anderson
    0.47
    Gön
    0.46
     G
    0.46
    TintMode
    0.45
    Autowired
    0.44
    Activations Density 0.140%

    No Known Activations