© 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. 23265
    Prev
    Next
    INDEX
    Explanations

    instances of the word "counsel" or related legal terminology

    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
    RequestType
    -0.52
    pya
    -0.50
     off
    -0.49
    LoginPage
    -0.49
     사
    -0.48
    UIAlert
    -0.45
     originally
    -0.44
    gab
    -0.44
    InfoService
    -0.44
     newVal
    -0.44
    POSITIVE LOGITS
    endphp
    0.98
    sizeCache
    0.94
    })`
    0.85
     виправивши
    0.82
    ReusableCell
    0.82
    Hentet
    0.81
    stalgia
    0.78
     AssemblyCompany
    0.77
    >--}}
    0.76
     RDC
    0.75
    Activations Density 0.000%

    No Known Activations