© 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. 0-RES-MATRYOSHKA-DC
    7. 13195
    Prev
    Next
    INDEX
    Explanations

    specific symbols and characters, likely for identifying formatting or special tokens

    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
    tvguidetime
    -0.77
     myſelf
    -0.73
     ſtate
    -0.67
     createState
    -0.66
     Alha
    -0.65
    parsedMessage
    -0.65
    ſelf
    -0.65
     Whitehead
    -0.65
     houſe
    -0.65
    principalColumn
    -0.64
    POSITIVE LOGITS
     Rap
    0.75
    MeasureSpec
    0.73
     acceptor
    0.69
    Rap
    0.68
     limp
    0.62
    strophy
    0.62
    orbit
    0.62
    hskip
    0.61
     Reich
    0.60
    pyl
    0.60
    Activations Density 0.117%

    No Known Activations