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. 15513
    Prev
    Next
    INDEX
    Explanations

    the use of links or references in documentation or code comments

    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
     nahilalakip
    -0.80
     تانيه
    -0.76
     оригіналу
    -0.75
    webElement
    -0.74
     ModelExpression
    -0.70
    ClientRect
    -0.68
    extAlignment
    -0.67
    aság
    -0.67
    STERS
    -0.66
    Архівовано
    -0.64
    POSITIVE LOGITS
    bkz
    0.54
    addComponent
    0.51
    årige
    0.50
    ​
    0.50
     Vah
    0.49
     Sce
    0.48
     cref
    0.48
    link
    0.46
    toHave
    0.46
    twimg
    0.46
    Activations Density 0.002%

    No Known Activations