© 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. 24674
    Prev
    Next
    INDEX
    Explanations

    first-person perspective statements and expressions of personal experience

    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
    BeginContext
    -0.81
     CURIAM
    -0.81
    ंदीखरीदारी
    -0.67
    ">//
    -0.67
     Савезне
    -0.66
    省市镇
    -0.65
    )|^{
    -0.64
    devamını
    -0.63
     AssemblyCulture
    -0.63
     دیکھیے
    -0.63
    POSITIVE LOGITS
    viembre
    0.52
     OLE
    0.51
     konkurs
    0.49
    CES
    0.49
    Atsauces
    0.48
     distanza
    0.47
    lusst
    0.47
     CORS
    0.47
    fraid
    0.47
    ajaan
    0.46
    Activations Density 0.059%

    No Known Activations