© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4423
    Prev
    Next
    INDEX
    Explanations

    references to patents and legal documents

    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
     CreateTagHelper
    -1.13
     تانيه
    -1.00
     InputDecoration
    -0.95
     مرئيه
    -0.87
    WireFormatLite
    -0.81
    rungsseite
    -0.78
     صوتيه
    -0.78
     propOrder
    -0.77
    OGND
    -0.77
    MLLoader
    -0.76
    POSITIVE LOGITS
     previous
    0.56
    metto
    0.46
    prnewswire
    0.46
     false
    0.46
     front
    0.46
     mandatory
    0.46
    шень
    0.45
    putBoolean
    0.45
     buzz
    0.44
    وري
    0.44
    Activations Density 0.018%

    No Known Activations