© 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. 14940
    Prev
    Next
    INDEX
    Explanations

    ratings and numerical values associated with reviews

    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
    Referencies
    -0.60
    ticum
    -0.56
    AndEndTag
    -0.56
    Leírás
    -0.54
     RU
    -0.53
    Manbalar
    -0.53
    stande
    -0.53
    پاسخ
    -0.52
    }`).
    -0.52
     別注
    -0.52
    POSITIVE LOGITS
    abstractmethod
    0.49
     STARS
    0.48
     स्टार
    0.46
    otonin
    0.45
    tift
    0.45
     chì
    0.45
     stars
    0.45
     indisponible
    0.45
    STAR
    0.45
    rowned
    0.44
    Activations Density 0.007%

    No Known Activations