© 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. 56
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to documentation, data, and specifications in technical fields like programming, engineering, or science.

    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
    __(/*!
    -0.75
    󠁿
    -0.69
     
    -0.67
     تضيفلها
    -0.66
    HEET
    -0.63
    IATION
    -0.62
    SerializedName
    -0.61
    licant
    -0.61
    ISTRATION
    -0.61
    OrEqualTo
    -0.60
    POSITIVE LOGITS
     ſche
    0.79
     Reſ
    0.76
     itſelf
    0.71
     houſe
    0.69
     ―――――
    0.69
     Diſ
    0.68
     ſy
    0.68
     ſch
    0.66
     Perſ
    0.65
     Houſe
    0.64
    Activations Density 26.819%

    No Known Activations