© 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. 92
    Prev
    Next
    INDEX
    Explanations

    words that can indicate the article contains technical content

    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
     Kurds
    -0.89
     Roskov
    -0.85
     geologists
    -0.81
     CreateTagHelper
    -0.80
    abestanden
    -0.80
     sherds
    -0.79
     ModelExpression
    -0.79
     anthropologists
    -0.79
     définiti
    -0.77
    InjectAttribute
    -0.77
    POSITIVE LOGITS
    eſt
    0.98
    ness
    0.98
    적인
    0.86
     individual
    0.85
     human
    0.85
    leſs
    0.83
     form
    0.83
    neſs
    0.82
     regional
    0.80
    ly
    0.80
    Activations Density 9.770%

    No Known Activations