© 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. 1-CLT-HP
    7. 14151
    Prev
    Next
    INDEX
    Explanations

    confluence

    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
     confluence
    -0.98
    fluence
    -0.80
     conflu
    -0.66
    XmlAccessType
    -0.57
    bouncycastle
    -0.54
    ffles
    -0.52
    znej
    -0.51
    mapStateToProps
    -0.50
    FieldSet
    -0.48
    äch
    -0.48
    POSITIVE LOGITS
     zone
    0.55
    comuna
    0.54
    تفصیلات
    0.52
     EClass
    0.51
     समीक्षक
    0.50
     CWE
    0.49
     rhestr
    0.49
    AnchorStyles
    0.49
     WebDriverWait
    0.49
    ScopeManager
    0.48
    Activations Density 0.011%

    No Known Activations