© 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. 25887
    Prev
    Next
    INDEX
    Explanations

    references to material properties and their behaviors

    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
    Pautan
    -0.59
    bkz
    -0.54
    rungsseite
    -0.52
     devenus
    -0.51
    glGet
    -0.51
     engraçadas
    -0.50
     requestCode
    -0.50
     Nare
    -0.49
     resisting
    -0.49
     téléchargez
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    省市镇
    0.63
    GIVEREF
    0.60
    Personendaten
    0.60
    toMatchSnapshot
    0.56
    adaptiveStyles
    0.55
    ituary
    0.54
     <>",
    0.54
    :✨
    0.53
    Jeografia
    0.53
    Activations Density 0.019%

    No Known Activations