© 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. 244
    Prev
    Next
    INDEX
    Explanations

    sentences in the third person in historical contexts

    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
     weren
    -0.62
     aren
    -0.57
     confused
    -0.54
     gotten
    -0.51
    simpleType
    -0.50
     kinda
    -0.49
     freaked
    -0.49
     pivo
    -0.49
     gitti
    -0.49
     froze
    -0.48
    POSITIVE LOGITS
    GOTREF
    0.83
     ModelExpression
    0.69
     Wikimedijinoj
    0.68
    ſelves
    0.67
    pidou
    0.67
    RenderAtEndOf
    0.66
    webElementXpaths
    0.65
    ReusableCell
    0.64
     MainAxisSize
    0.64
     /\.(
    0.62
    Activations Density 1.305%

    No Known Activations