© 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. 803
    Prev
    Next
    INDEX
    Explanations

    French words and phrases, particularly in informal or conversational contexts, as well as some emoticons and symbols used online

    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
     inoxydable
    -0.58
     interior
    -0.56
     abstrait
    -0.51
     este
    -0.50
     del
    -0.49
     téléph
    -0.47
     nôtre
    -0.47
     superior
    -0.47
     asiatique
    -0.46
     inferior
    -0.46
    POSITIVE LOGITS
    :+:
    0.69
     physi
    0.68
     byz
    0.67
     Egal
    0.66
    isation
    0.65
     localisation
    0.61
    ể
    0.60
     aide
    0.60
     parties
    0.59
     philanthrop
    0.58
    Activations Density 0.607%

    No Known Activations