© 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. 9467
    Prev
    Next
    INDEX
    Explanations

    patterns related to future considerations and legal contexts

    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
    andExpect
    -0.53
    toThrow
    -0.49
     gerekiyor
    -0.47
     vairāk
    -0.46
    밖
    -0.45
     uscita
    -0.45
     this
    -0.45
     stressing
    -0.45
     äm
    -0.45
     bellezza
    -0.44
    POSITIVE LOGITS
     يتيمه
    1.00
     للمعارف
    0.79
     lenker
    0.75
    Derp
    0.72
    PageRoute
    0.69
    yntaxException
    0.68
    esModule
    0.68
    aarrggbb
    0.68
    WebVitals
    0.67
    LElement
    0.67
    Activations Density 0.017%

    No Known Activations