© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92711
    Prev
    Next
    INDEX
    Explanations

    ide

    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
    ide
    -1.13
    IDE
    -0.82
    NE
    -0.70
     punches
    -0.69
     punch
    -0.65
     punching
    -0.65
     IDE
    -0.64
    idé
    -0.62
     NE
    -0.61
     referenties
    -0.59
    POSITIVE LOGITS
    AndEndTag
    0.80
     invokingState
    0.70
     BrowserModule
    0.68
    protoimpl
    0.65
    MenuInflater
    0.63
    WebControls
    0.62
    SPATH
    0.62
    HandlerContext
    0.61
     snippetHide
    0.56
    gwt
    0.54
    Activations Density 0.082%

    No Known Activations