© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    personal names and important identifiers in a biographical context

    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
    +#+#
    -0.57
    Viitteet
    -0.54
    ագրություններ
    -0.53
     already
    -0.51
    \{\\
    -0.50
     дописавши
    -0.49
    ungo
    -0.48
    ÁRIO
    -0.48
    Autoritní
    -0.48
    Przeczytaj
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.69
     للاسماء
    0.67
    >>();
    0.60
     Sched
    0.59
     HMI
    0.55
    ...");
    0.53
     BrowserModule
    0.53
    ...");
    0.53
     autoradio
    0.53
    ulose
    0.53
    Activations Density 0.016%

    No Known Activations