© 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. 16311
    Prev
    Next
    INDEX
    Explanations

    terms related to laboratory procedures and experimental protocols

    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
    <bos>
    -0.62
    avat
    -0.52
    ysacchar
    -0.46
    ुनिया
    -0.46
    ScopeManager
    -0.45
    ngr
    -0.45
     mẽ
    -0.45
    URLException
    -0.44
    ceğini
    -0.44
     Calla
    -0.44
    POSITIVE LOGITS
    ьаж
    0.74
     Roskov
    0.70
    parsedMessage
    0.68
     Италијани
    0.59
     Wikimedijinoj
    0.58
     &___
    0.57
     CreateTagHelper
    0.56
     Dernière
    0.56
     Italijani
    0.56
    KURZBESCHREIBUNG
    0.55
    Activations Density 0.057%

    No Known Activations