© 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. 6-RES-MATRYOSHKA-DC
    7. 735
    Prev
    Next
    INDEX
    Explanations

    the character '€' which may indicate the presence of non-standard encoding

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ©️
    -0.79
     répondu
    -0.79
    InSection
    -0.79
     jLabel
    -0.78
     Drapeau
    -0.77
     GTS
    -0.75
     joaat
    -0.75
    MeasureSpec
    -0.75
     Baillargeon
    -0.74
     springfox
    -0.73
    POSITIVE LOGITS
    €
    2.03
    
    0.71
    escu
    0.65
    EAR
    0.65
     EAR
    0.65
    OrDefault
    0.63
     imageNamed
    0.62
    btnNew
    0.61
     mental
    0.61
     htmlFor
    0.60
    Activations Density 0.003%

    No Known Activations