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. 303
    Prev
    Next
    INDEX
    Explanations

    scientific terms and details related to experimental protocols and results

    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
    CloseOperation
    -0.85
     meriva
    -0.79
    tableFuture
    -0.78
    yarnpkg
    -0.77
     Diar
    -0.76
    uchy
    -0.75
    marle
    -0.75
    tude
    -0.75
    binant
    -0.74
    ähkö
    -0.74
    POSITIVE LOGITS
    ses
    1.02
     getS
    1.01
    s
    0.98
     Sas
    0.96
    nes
    0.94
    es
    0.91
    hes
    0.91
     PPS
    0.91
    iS
    0.90
    GS
    0.89
    Activations Density 3.674%

    No Known Activations