© 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. 1568
    Prev
    Next
    INDEX
    Explanations

    Romanian names and addresses

    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
     myſelf
    -0.81
     purpoſe
    -0.79
     pleaſure
    -0.77
     juſ
    -0.74
     ragaz
    -0.74
     Diſ
    -0.73
     Jefus
    -0.72
     Monfieur
    -0.71
     themſelves
    -0.71
     Anſ
    -0.70
    POSITIVE LOGITS
     în
    0.56
     „
    0.46
    Citiți
    0.45
     În
    0.42
     și
    0.42
     implicitly
    0.41
     ie
    0.41
    urator
    0.41
     fire
    0.41
     faixa
    0.41
    Activations Density 0.131%

    No Known Activations