© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21564
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completeness or totality

    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
    GenerationType
    -0.90
     Homem
    -0.77
    
    -0.71
    unnitel
    -0.69
    ball
    -0.67
    west
    -0.66
     much
    -0.66
    block
    -0.66
    big
    -0.66
     West
    -0.65
    POSITIVE LOGITS
     Fully
    0.93
     متحده
    0.92
    Fully
    0.87
    RenderAtEndOf
    0.87
     fully
    0.84
    Pyx
    0.75
    {}/
    0.73
    "><?=
    0.72
    FULLY
    0.72
    astify
    0.72
    Activations Density 0.010%

    No Known Activations