© 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. 11227
    Prev
    Next
    INDEX
    Explanations

    search-related activities and terms

    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
    unsaturated
    -0.51
    мили
    -0.50
    возь
    -0.49
    createFrom
    -0.46
     Zä
    -0.46
     http
    -0.46
     our
    -0.45
    isSuccessful
    -0.45
     useful
    -0.44
     Gesch
    -0.44
    POSITIVE LOGITS
    出版年
    0.77
    ⓘ
    0.75
     propOrder
    0.69
     Réponses
    0.66
    setVerticalGroup
    0.66
     createSprite
    0.66
     Савезне
    0.65
     ApiException
    0.65
    IsMutable
    0.64
    HasColumnName
    0.62
    Activations Density 0.027%

    No Known Activations