© 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. 12-RES-MATRYOSHKA-DC
    7. 8550
    Prev
    Next
    INDEX
    Explanations

    terms related to online dating services and connections

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sp
    -0.45
     boletos
    -0.45
    jsdelivr
    -0.43
    DoubleQuotes
    -0.43
    手
    -0.42
     memoria
    -0.41
     reten
    -0.41
     L
    -0.41
     ver
    -0.41
     Re
    -0.39
    POSITIVE LOGITS
     ſtate
    0.86
     Tinder
    0.83
     Efq
    0.82
     pleaſure
    0.81
     Dating
    0.77
     ―――――
    0.77
     ftate
    0.74
     Monfieur
    0.74
     purpoſe
    0.73
     Theſe
    0.73
    Activations Density 0.036%

    No Known Activations