© 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. 22-RES-MATRYOSHKA-DC
    7. 1715
    Prev
    Next
    INDEX
    Explanations

    a few different phrases: "in vivo," "in vitro," statistical values, "please," "directly," and "RNA design."

    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.22.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.22.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
     }}</
    -0.66
     **
    -0.54
     старости
    -0.52
    SourceChecksum
    -0.51
    GTCX
    -0.50
     }}">
    -0.49
     öppna
    -0.49
    ☞
    -0.48
    PerformLayout
    -0.48
     quæ
    -0.48
    POSITIVE LOGITS
    /,
    0.75
     فريبيس
    0.72
    
    0.70
    </>
    0.69
    CodedInputStream
    0.68
    RenderAtEndOf
    0.65
    _);
    0.65
    //}
    0.63
    AddTagHelper
    0.62
    /.
    0.59
    Activations Density 1.686%

    No Known Activations