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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 31656
    Prev
    Next
    INDEX
    Explanations

    verbs associated with API actions such as creating, updating, deleting, handling, validating, and sending requests

    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
     Normdatei
    -0.85
     itſelf
    -0.79
     ALR
    -0.74
     octavia
    -0.74
     ་་
    -0.72
    WebElementEntity
    -0.71
     DPM
    -0.71
     ―――――
    -0.71
     CTS
    -0.71
     CTP
    -0.70
    POSITIVE LOGITS
    
    0.57
     <<<<<<<<<<<<<<
    0.54
     the
    0.53
     cầm
    0.50
    sslich
    0.50
     before
    0.49
    leski
    0.46
    oflavin
    0.46
    ConfigureAwait
    0.45
     The
    0.45
    Activations Density 0.003%

    No Known Activations