© 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. 19745
    Prev
    Next
    INDEX
    Explanations

    references to content previews

    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
    Discografia
    -0.92
    parsedMessage
    -0.90
    脚注の使い方
    -0.88
    valbard
    -0.86
     MotionEvent
    -0.84
    MessageOf
    -0.84
    ButtonModule
    -0.84
    AccessorTable
    -0.82
    icoot
    -0.81
     InputDecoration
    -0.79
    POSITIVE LOGITS
     Preview
    1.55
     preview
    1.55
    Preview
    1.43
     previews
    1.32
    PREVIEW
    1.31
    preview
    1.29
     PREVIEW
    1.27
     Sni
    1.04
    预览
    1.03
    Previews
    0.98
    Activations Density 0.005%

    No Known Activations