© 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. 31
    Prev
    Next
    INDEX
    Explanations

    code snippets, URLs, and file paths

    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
    endregion
    -0.70
    -------------</
    -0.69
    SerializedSize
    -0.69
    PointerException
    -0.68
     “
    -0.68
     
    -0.66
     "
    -0.66
    RegistryLite
    -0.65
    EReference
    -0.65
    TagMode
    -0.64
    POSITIVE LOGITS
     houſe
    0.96
     Reſ
    0.91
     Diſ
    0.90
     purpoſe
    0.89
     Houſe
    0.88
    ſelf
    0.88
     ſche
    0.83
     Efq
    0.82
     Anſ
    0.82
     iſt
    0.82
    Activations Density 5.895%

    No Known Activations