© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 583
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and symbols from various programming 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
     ſtate
    -0.90
     pleaſure
    -0.89
     purpoſe
    -0.86
     greateſt
    -0.84
     houſe
    -0.79
     ſche
    -0.78
     itſelf
    -0.77
    Personensuche
    -0.77
     ſever
    -0.76
     fevere
    -0.73
    POSITIVE LOGITS
     temp
    0.82
     s
    0.77
     tmp
    0.76
     r
    0.75
     t
    0.74
     res
    0.73
     p
    0.73
     c
    0.71
     v
    0.69
     result
    0.68
    Activations Density 0.963%

    No Known Activations