© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    the character 'x' followed immeaditely by another symbol

    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
    contentLoaded
    -0.91
    parsedMessage
    -0.86
    WriteAttribute
    -0.74
     EconPapers
    -0.73
    InSection
    -0.69
     initComponents
    -0.68
     ReactDOM
    -0.67
    RenderAtEndOf
    -0.67
    下载附件
    -0.66
    enumii
    -0.66
    POSITIVE LOGITS
    NUMX
    0.53
    mitte
    0.50
    idation
    0.50
    anthin
    0.49
     Sexton
    0.48
    peria
    0.47
    leetcode
    0.47
     par
    0.46
    viii
    0.46
    ?}",
    0.46
    Activations Density 0.318%

    No Known Activations