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. 19000
    Prev
    Next
    INDEX
    Explanations

    references to virus proteins and their 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
    er
    -0.92
     Mora
    -0.83
     Pata
    -0.75
    ly
    -0.73
     Talon
    -0.73
    ulihan
    -0.73
     Merlin
    -0.73
    HomeAsUpEnabled
    -0.72
    ,$_
    -0.70
     Sabine
    -0.69
    POSITIVE LOGITS
     NS
    1.62
    NS
    1.22
    providedIn
    1.09
    AutoresizingMask
    1.09
     ns
    0.86
    ServletException
    0.80
    __':
    0.78
     Scotia
    0.74
     NSM
    0.73
     Woolf
    0.71
    Activations Density 0.015%

    No Known Activations