© 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. 190
    Prev
    Next
    INDEX
    Explanations

    emphasized phrases focusing on personal experience and opinion

    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
    findpost
    -0.80
    LikeLike
    -0.78
    =$?
    -0.74
    LabelTagHelper
    -0.71
     betweenstory
    -0.69
     MenuItem
    -0.67
     guacamole
    -0.67
     Bulg
    -0.66
    hyung
    -0.66
     Dooley
    -0.66
    POSITIVE LOGITS
     Just
    1.05
     JUST
    1.05
    JUST
    1.04
     just
    1.01
    Just
    1.01
    just
    0.98
     simple
    0.94
     merely
    0.93
     simply
    0.92
    脚注の使い方
    0.91
    Activations Density 0.901%

    No Known Activations