© 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. 25696
    Prev
    Next
    INDEX
    Explanations

    references to decisions or choices available in a given 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
    mybatisplus
    -0.85
     itſelf
    -0.83
     initComponents
    -0.77
    WebElementEntity
    -0.77
    oubted
    -0.75
    Демографія
    -0.72
    OGND
    -0.71
    ondern
    -0.69
     Spisak
    -0.69
     détru
    -0.68
    POSITIVE LOGITS
     alternative
    0.54
    法的
    0.47
     alternatives
    0.46
     Test
    0.45
     option
    0.43
    Alternative
    0.42
     method
    0.42
    办法
    0.42
     विकल्प
    0.41
     test
    0.41
    Activations Density 0.079%

    No Known Activations