© 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. 543
    Prev
    Next
    INDEX
    Explanations

    terms related to research methodology and filtering criteria

    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
    WithIOException
    -0.75
    ніципалі
    -0.73
     EconPapers
    -0.73
     Réponses
    -0.58
    раздо
    -0.57
     /#
    -0.56
     @}
    -0.56
    itinéraire
    -0.56
     INTERESAR
    -0.55
     ExecuteAsync
    -0.54
    POSITIVE LOGITS
     criteria
    1.27
     Criteria
    1.06
     criterion
    1.02
    criteria
    0.97
     CRITERIA
    0.95
     criter
    0.93
    Criteria
    0.92
     conditions
    0.90
    条件
    0.84
    criterion
    0.84
    Activations Density 2.199%

    No Known Activations