© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5388
    Prev
    Next
    INDEX
    Explanations

    autobiographical memories and personal reflections

    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
    ArgsConstructor
    -0.71
    Background
    -0.66
     backing
    -0.63
    background
    -0.63
     Backing
    -0.61
     Background
    -0.60
     AssemblyTitle
    -0.58
     backgrounds
    -0.57
     Behind
    -0.57
     Hintergrund
    -0.57
    POSITIVE LOGITS
     down
    0.84
     back
    0.73
     tilbake
    0.59
    Tembelea
    0.58
     tillbaka
    0.57
    Nuorodos
    0.56
    🏻‍♀️
    0.54
    følgelig
    0.54
    ĵ
    0.54
     else
    0.54
    Activations Density 0.046%

    No Known Activations