© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 31075
    Prev
    Next
    INDEX
    Explanations

    terms related to parental rights and citizenship status, particularly in the context of unwed parents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.80
    новниш
    -0.77
    SerializedName
    -0.71
     <=",
    -0.71
     FetchType
    -0.70
     mergeFrom
    -0.70
    原始内容存档于
    -0.68
    windowFixed
    -0.68
    انيف
    -0.66
     تضيفلها
    -0.66
    POSITIVE LOGITS
    ualla
    0.46
     desaf
    0.45
    conos
    0.43
    ylül
    0.43
     Maury
    0.43
     základ
    0.42
    casio
    0.42
     papir
    0.41
    pakk
    0.40
     grå
    0.40
    Activations Density 0.078%

    No Known Activations