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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16712
    Prev
    Next
    INDEX
    Explanations

    mentions of a dog named Spike along with related words such as licking, sniffing, licking, or related dog breeds.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.91
     childrens
    -0.90
     child
    -0.84
    ьаж
    -0.82
    child
    -0.81
     childs
    -0.81
     children
    -0.81
     Children
    -0.80
    AnchorStyles
    -0.79
    AddTagHelper
    -0.79
    POSITIVE LOGITS
    勲
    0.54
    退休
    0.47
     Retired
    0.45
     retired
    0.43
     tác
    0.43
    Το
    0.41
     sağ
    0.40
    apura
    0.40
    phases
    0.40
     retiring
    0.40
    Activations Density 0.033%

    No Known Activations