© 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. 13919
    Prev
    Next
    INDEX
    Explanations

    references to a significant or enduring period or quality

    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
     ब्रेकडाउन
    -0.69
    abestanden
    -0.65
    ResumeLayout
    -0.63
     <>",
    -0.60
    σιμοποι
    -0.59
     entanto
    -0.58
     Majestic
    -0.55
    ėk
    -0.54
    neapolis
    -0.54
    presence
    -0.53
    POSITIVE LOGITS
     lifelong
    2.73
     longtime
    2.28
     longstanding
    1.45
    elong
    0.78
     boyhood
    0.73
    lif
    0.69
     Lif
    0.67
     (;;)
    0.66
    Lif
    0.66
     childhood
    0.63
    Activations Density 0.001%

    No Known Activations