© 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. 0-RES-MATRYOSHKA-DC
    7. 13912
    Prev
    Next
    INDEX
    Explanations

    references to the process or occurrence of descent or downward movement

    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
    desc
    -1.21
     desc
    -0.88
    Desc
    -0.84
    Asc
    -0.73
     ascent
    -0.69
    asc
    -0.68
     asc
    -0.63
    DESC
    -0.62
    PerformLayout
    -0.57
    hassee
    -0.57
    POSITIVE LOGITS
     descending
    1.95
    descending
    1.05
    pic
    0.68
     Pic
    0.66
     descends
    0.62
     صوتيه
    0.60
     pic
    0.60
    documentclass
    0.59
    Argb
    0.58
    writeObject
    0.58
    Activations Density 0.001%

    No Known Activations