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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15827
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that are likely to represent encoded or stylized text patterns, possibly including special characters, non-Latin scripts, or symbols

    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
    uxxxx
    -0.67
     Efq
    -0.66
    FTFY
    -0.65
    WireFormatLite
    -0.64
    DockStyle
    -0.64
    CodedInputStream
    -0.61
     '\\;'
    -0.60
    HomeAsUpEnabled
    -0.60
     poffe
    -0.59
    دانشنامهٔ
    -0.59
    POSITIVE LOGITS
    ë
    3.78
    ën
    2.95
    ër
    1.73
    ës
    1.55
    ënt
    1.52
    Ë
    1.47
    ët
    1.38
    ël
    1.30
     ë
    1.02
    ëren
    0.98
    Activations Density 0.000%

    No Known Activations