© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16096
    Prev
    Next
    INDEX
    Explanations

    conversational exchanges with specific names and greetings

    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
    protoimpl
    -0.54
     متعلقه
    -0.51
    werker
    -0.50
     PARSER
    -0.49
    Дереккөздер
    -0.49
    usages
    -0.48
     Mill
    -0.47
     cháy
    -0.46
    ̀u
    -0.46
    fvar
    -0.45
    POSITIVE LOGITS
     />\
    0.62
     Efq
    0.61
     Superhost
    0.58
     cherchés
    0.58
     Theſe
    0.58
     ainfi
    0.57
     greateſt
    0.55
     faſt
    0.55
     myſelf
    0.55
     ffilm
    0.54
    Activations Density 0.003%

    No Known Activations