© 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. 29
    Prev
    Next
    INDEX
    Explanations

    various snippets of code from a variety of languages

    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
     CGPoint
    -0.81
     setw
    -0.79
     irq
    -0.78
     photolibrary
    -0.77
     rospy
    -0.72
     vnode
    -0.72
     userSchema
    -0.71
     hwnd
    -0.70
     clearColor
    -0.68
     isNameExpr
    -0.66
    POSITIVE LOGITS
     get
    0.91
     ((
    0.85
     _
    0.82
     new
    0.81
     false
    0.78
    calypse
    0.76
     !
    0.75
     /*
    0.74
    houding
    0.74
     null
    0.71
    Activations Density 5.966%

    No Known Activations