© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97062
    Prev
    Next
    INDEX
    Explanations

    conne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conne
    -0.71
     Bai
    -0.56
    Bai
    -0.55
    ecirc
    -0.48
    shi
    -0.48
    tagext
    -0.48
     toile
    -0.46
     ProtoMessage
    -0.46
     lenker
    -0.45
     doInBackground
    -0.44
    POSITIVE LOGITS
     Cros
    0.57
    ುತ್ತ
    0.57
     resultCode
    0.57
     Cross
    0.57
    americanos
    0.56
    Predecesor
    0.56
    :+:
    0.53
    новништво
    0.53
    énario
    0.52
     Lep
    0.52
    Activations Density 0.495%

    No Known Activations