© 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. 22-RES-MATRYOSHKA-DC
    7. 2949
    Prev
    Next
    INDEX
    Explanations

    mentions of "girl" and related terms in the context of the attention of others, especially men, or in relation to musical performance.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    小子
    -0.62
     shit
    -0.62
     fuckin
    -0.57
     nigga
    -0.57
    Damn
    -0.56
    老子
    -0.56
     man
    -0.56
     istrinya
    -0.55
     damn
    -0.53
    俺
    -0.52
    POSITIVE LOGITS
    expandindo
    0.83
    principalTable
    0.77
    QMetaType
    0.75
     виправивши
    0.67
     Auntie
    0.65
    ///</
    0.63
     lovely
    0.63
    rigada
    0.63
    AntiForgeryToken
    0.62
    очень
    0.61
    Activations Density 0.039%

    No Known Activations