© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 203
    Prev
    Next
    INDEX
    Explanations

    references to specific dates or time points

    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
    dataclass
    -0.50
    Ҭ
    -0.50
     momentos
    -0.46
     Welle
    -0.46
    offsetof
    -0.45
    ॉप
    -0.44
    силь
    -0.44
    Vidite
    -0.43
     Empieza
    -0.43
    Története
    -0.43
    POSITIVE LOGITS
     October
    3.39
     July
    3.36
     September
    3.33
     November
    3.31
     June
    3.30
     April
    3.28
     February
    3.27
     January
    3.23
     December
    3.23
     August
    3.22
    Activations Density 0.624%

    No Known Activations