© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 278
    Prev
    Next
    INDEX
    Explanations

    key terms related to methodologies and their effectiveness in research or practices

    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
     myſelf
    -1.23
     ſever
    -1.08
     purpoſe
    -1.05
    تقاوى
    -1.05
     itſelf
    -1.05
     Efq
    -1.04
     Shakspeare
    -1.02
     فريبيس
    -1.02
     ſtate
    -1.02
     fubject
    -1.02
    POSITIVE LOGITS
     a
    1.01
    :
    1.01
     the
    0.87
     an
    0.83
     
    0.81
     either
    0.79
     two
    0.71
     simply
    0.69
     “
    0.66
     is
    0.63
    Activations Density 4.538%

    No Known Activations