© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18682
    Prev
    Next
    INDEX
    Explanations

    expressions of feeling or recognition related to shared experiences

    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
    Negative Logits
    GEBURTSDATUM
    -1.03
     unknownFields
    -0.98
    parsedMessage
    -0.87
    tagHelperRunner
    -0.79
    CppMethod
    -0.74
    fjspx
    -0.74
    EndInit
    -0.72
    tonode
    -0.71
    featureID
    -0.69
    SerializedSize
    -0.69
    POSITIVE LOGITS
    Кры
    0.44
    ёз
    0.44
    NOPQRST
    0.43
     [
    0.43
    ِّف
    0.42
     kasarigan
    0.41
    zulegen
    0.40
     Paglinawan
    0.40
    ându
    0.39
    /***/
    0.39
    Activations Density 0.054%

    No Known Activations