© 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. 19583
    Prev
    Next
    INDEX
    Explanations

    discussions about personal experiences and reflections

    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
     الحره
    -0.95
     '\\;'
    -0.79
    الإنجليزية
    -0.70
     resourceCulture
    -0.69
    ⓧ
    -0.68
     كومونز
    -0.65
     Савезне
    -0.64
     uſed
    -0.64
    keyColumn
    -0.63
    ]--;
    -0.63
    POSITIVE LOGITS
     Glaser
    0.45
    ponses
    0.45
    äls
    0.45
     bước
    0.44
    ']):
    0.44
    yntaxException
    0.43
    mester
    0.41
     suivantes
    0.41
    StrictMode
    0.41
    lacht
    0.41
    Activations Density 0.019%

    No Known Activations