© 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. 18-RES-MATRYOSHKA-DC
    7. 239
    Prev
    Next
    INDEX
    Explanations

    words related to roles or professions

    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.18.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.18.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
    WebVitals
    -0.71
    PreferredItem
    -0.71
    TagMode
    -0.66
    újo
    -0.64
    httphttps
    -0.64
     PyTuple
    -0.63
     Taktlose
    -0.61
    SaveChanges
    -0.59
    исленность
    -0.57
    urilor
    -0.55
    POSITIVE LOGITS
     Efq
    0.79
    unner
    0.69
    🏼
    0.68
    🏾
    0.67
     extraordinaire
    0.67
     Theſe
    0.63
    🏽
    0.62
    ſhip
    0.62
    iented
    0.61
    Schüler
    0.61
    Activations Density 2.994%

    No Known Activations