Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 28612
    Prev
    Next
    INDEX
    Explanations

    references to transmembrane proteins and their related characteristics

    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
     TypeError
    -0.46
    tonsoft
    -0.45
     all
    -0.43
     analytically
    -0.43
    osome
    -0.41
     Hotspot
    -0.40
    散
    -0.40
     critical
    -0.40
     Bonnet
    -0.39
     evidence
    -0.38
    POSITIVE LOGITS
     transmembrane
    0.84
     betweenstory
    0.84
     ujednoznacz
    0.81
    MessageTagHelper
    0.77
     kaarangay
    0.76
     Bioaccumulative
    0.74
     vPvB
    0.74
    MemoryWarning
    0.74
     SwitchCompat
    0.74
    __':
    
    0.73
    Activations Density 0.012%

    No Known Activations