© 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. 3-RES-MATRYOSHKA-DC
    7. 400
    Prev
    Next
    INDEX
    Explanations

    certainly looking for how. It has a fondness for the word "meth," too, but "how" is definitely the stronger signal

    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
     Schulte
    -0.70
    DataMember
    -0.68
    Richie
    -0.67
     firebaseConfig
    -0.63
    irre
    -0.63
    Personensuche
    -0.63
    قایناق‌لار
    -0.63
     isset
    -0.62
    valbard
    -0.61
     teş
    -0.61
    POSITIVE LOGITS
     how
    2.56
     ways
    2.05
     How
    1.95
     HOW
    1.94
    how
    1.91
    How
    1.89
    HOW
    1.81
     way
    1.71
     WAYS
    1.70
     Ways
    1.68
    Activations Density 1.146%

    No Known Activations