© 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. 24-RES-MATRYOSHKA-DC
    7. 294
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms

    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.24.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.24.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
     rospy
    -0.61
    WebpackPlugin
    -0.58
    MLLoader
    -0.55
    Portale
    -0.53
    ContextHolder
    -0.51
    derung
    -0.50
    MessageTagHelper
    -0.50
     NSCoder
    -0.50
    NSYLVANIA
    -0.49
    ChildScrollView
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.72
    Tests
    0.67
     tests
    0.67
     Tests
    0.66
     analysis
    0.65
     analyses
    0.65
     Analyses
    0.63
    存于互联网档案馆
    0.63
     ANOVA
    0.63
     Significance
    0.61
    Activations Density 2.448%

    No Known Activations