© 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. 10863
    Prev
    Next
    INDEX
    Explanations

    text related to coding or programming tasks, especially involving modifications or implementations of code

    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
    出版年
    -0.97
    cookieParser
    -0.76
    __":
    -0.66
    nical
    -0.62
    homonymie
    -0.61
    ագրություններ
    -0.60
    lineno
    -0.60
    
    -0.59
    CloseOperation
    -0.59
    rungsseite
    -0.58
    POSITIVE LOGITS
     purposely
    0.66
    してみました
    0.65
     purposefully
    0.57
     hice
    0.54
     sauter
    0.53
     below
    0.53
     sengaja
    0.53
     entered
    0.52
     erred
    0.52
     hoping
    0.52
    Activations Density 0.195%

    No Known Activations