© 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. 5514
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future discussion or reference to upcoming content

    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
    #+#
    -0.61
    geving
    -0.52
    saraba
    -0.48
    incidence
    -0.47
     químicos
    -0.45
     simpel
    -0.45
    rethe
    -0.45
    henko
    -0.44
    umumkan
    -0.44
     incertidumbre
    -0.43
    POSITIVE LOGITS
    TypedDataSet
    0.83
     senere
    0.82
    MessageOf
    0.79
     CreateTagHelper
    0.77
     فريبيس
    0.77
    principalTable
    0.75
    RenderAtEndOf
    0.75
    parsedMessage
    0.74
    setVerticalGroup
    0.73
    HasIndex
    0.73
    Activations Density 0.288%

    No Known Activations