© 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. 3-RES-MATRYOSHKA-DC
    7. 1679
    Prev
    Next
    INDEX
    Explanations

    the word "of", sometimes more strongly when followed by words related to law

    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
     pasangan
    -0.47
     cerveau
    -0.47
     isolato
    -0.46
     navíc
    -0.45
     elettrico
    -0.44
     Drey
    -0.44
     мечты
    -0.44
     isolado
    -0.44
    各
    -0.43
    Penjelasan
    -0.43
    POSITIVE LOGITS
    ToAction
    0.83
    DrawerToggle
    0.67
    CURLOPT
    0.65
    AndEndTag
    0.65
    UIControlState
    0.64
    stateProvider
    0.63
     joaat
    0.63
    ambut
    0.61
    XMLSchema
    0.60
    ריכה
    0.60
    Activations Density 1.162%

    No Known Activations