© 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. 22-RES-MATRYOSHKA-DC
    7. 3100
    Prev
    Next
    INDEX
    Explanations

    words and phrases that reveal the author's sentiment, intentions, or opinions.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     odkazy
    -0.71
     فريبيس
    -0.65
    HasAnnotation
    -0.61
     betweenstory
    -0.61
     AssemblyCulture
    -0.59
     Вікі
    -0.59
     continúas
    -0.59
    intenant
    -0.58
     通販
    -0.57
    complexContent
    -0.56
    POSITIVE LOGITS
     someone
    3.52
    someone
    3.22
    Someone
    3.06
     Someone
    2.97
     somebody
    2.83
    somebody
    2.56
     alguien
    2.55
     SOMEONE
    2.53
     quelqu
    2.52
     alguém
    2.47
    Activations Density 0.630%

    No Known Activations