© 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. 1814
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, such as function declarations, callbacks, and commands

    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
    PHeader
    -0.49
    webElementGuid
    -0.44
    JsonInclude
    -0.44
    NOPQRST
    -0.42
    diti
    -0.42
    qrstuvwxyz
    -0.41
    ستون
    -0.41
    aparte
    -0.41
     Selig
    -0.41
    toBe
    -0.41
    POSITIVE LOGITS
     function
    1.77
    function
    1.59
     Function
    1.52
    函数
    1.47
    Function
    1.44
     functions
    1.44
     func
    1.43
    func
    1.37
     함수
    1.34
     FUNCTION
    1.34
    Activations Density 1.640%

    No Known Activations