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. 23902
    Prev
    Next
    INDEX
    Explanations

    button-related elements in a user interface

    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
     Bab
    -0.67
     Comer
    -0.65
    Comer
    -0.63
    Bab
    -0.62
     comer
    -0.60
     Sif
    -0.60
    ovka
    -0.58
    ص
    -0.58
    Crow
    -0.57
    šča
    -0.57
    POSITIVE LOGITS
     btn
    1.57
    btn
    1.17
     Btn
    1.06
     BTN
    1.05
    ########.
    1.02
    Btns
    0.96
     Yeats
    0.91
    BTN
    0.88
    Btn
    0.83
    ursos
    0.81
    Activations Density 0.005%

    No Known Activations