© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    phrases related to fixing errors

    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
    complexContent
    -0.55
    íma
    -0.48
    optString
    -0.46
     AssemblyProduct
    -0.46
    lorus
    -0.45
    Filmografie
    -0.45
    quie
    -0.45
    پیوند
    -0.43
    dubbo
    -0.43
     tunt
    -0.43
    POSITIVE LOGITS
     mistake
    2.50
     mistakes
    2.31
     error
    2.22
     incorrect
    2.19
     incorrectly
    2.17
     wrong
    2.16
     Mistake
    2.16
     errors
    2.13
    Mistake
    2.08
     mistaken
    2.06
    Activations Density 2.957%

    No Known Activations