© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 401
    Prev
    Next
    INDEX
    Explanations

    various classifications and types of objects or entities in a given context

    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
    only
    -0.54
    一枚
    -0.53
    ARROLLO
    -0.52
    ONLY
    -0.51
    inheritdoc
    -0.50
     only
    -0.50
     onCreateView
    -0.49
    Previews
    -0.47
    méno
    -0.47
     Millionaire
    -0.47
    POSITIVE LOGITS
     different
    0.94
     types
    0.93
    different
    0.81
     diferentes
    0.81
    Different
    0.80
     nakalista
    0.79
     including
    0.76
    ArrowToggle
    0.76
     ranging
    0.75
     Different
    0.75
    Activations Density 3.791%

    No Known Activations