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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 82
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific methodologies 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
     
    -0.92
      
    -0.66
    :
    -0.61
     a
    -0.58
     I
    -0.57
     "
    -0.57
     the
    -0.56
    ↵
    -0.56
    ↵↵
    -0.56
     BoxFit
    -0.55
    POSITIVE LOGITS
     Majefty
    1.05
     ſche
    1.04
     Reſ
    1.02
     ſever
    1.01
    Autoritní
    0.99
     raiſ
    0.98
     myſelf
    0.98
     Jefus
    0.97
     Conſ
    0.97
     fevere
    0.96
    Activations Density 29.967%

    No Known Activations