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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14506
    Prev
    Next
    INDEX
    Explanations

    references to sudden or rapid changes

    oai_token-act-pair · gpt-4.1-nano
    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
     kasarigan
    -1.02
     متعلقه
    -0.88
    findpost
    -0.82
     AssemblyTitle
    -0.81
    principalTable
    -0.80
     للمعارف
    -0.77
    DockStyle
    -0.76
    Datuak
    -0.74
     jadx
    -0.74
    useNewUrlParser
    -0.73
    POSITIVE LOGITS
     abrupt
    1.88
     abruptly
    1.68
     sharply
    1.59
     brus
    0.86
     резко
    0.81
     steeply
    0.79
     harshly
    0.69
     gradual
    0.65
     curt
    0.65
     flatly
    0.62
    Activations Density 0.003%

    No Known Activations