© 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. 5482
    Prev
    Next
    INDEX
    Explanations

    information related to social media and online interactions

    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
    ChildScrollView
    -0.49
     سلام
    -0.46
    issants
    -0.45
    니다
    -0.44
    ".
    -0.44
     Aps
    -0.44
     رت
    -0.43
    يمي
    -0.43
     owner
    -0.42
     vertes
    -0.42
    POSITIVE LOGITS
     للمعارف
    1.10
    ⓧ
    0.91
    GEBURTSDATUM
    0.83
     تانيه
    0.81
     <<<<<<<<<<<<<<
    0.77
    APORE
    0.77
     EconPapers
    0.76
    Hentet
    0.74
    حوالہ
    0.70
    RegressionTest
    0.69
    Activations Density 0.706%

    No Known Activations