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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16321
    Prev
    Next
    INDEX
    Explanations

    topics related to early life and education

    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
     MainAxisSize
    -0.61
     Paglinawan
    -0.48
     विश्वसनीयता
    -0.48
    cookieParser
    -0.47
     Agamemnon
    -0.47
    VersionUID
    -0.47
    Économie
    -0.46
     SwitchCompat
    -0.46
    gration
    -0.45
    äsident
    -0.45
    POSITIVE LOGITS
    EndContext
    0.73
    TypedDataSet
    0.71
     Audiodateien
    0.67
    InjectAttribute
    0.65
    tagHelperRunner
    0.64
    حياته
    0.60
    lidean
    0.60
    حياتها
    0.60
    enseits
    0.60
    قایناق‌لار
    0.57
    Activations Density 0.004%

    No Known Activations