© 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. 20-CLT-HP
    7. 72112
    Prev
    Next
    INDEX
    Explanations

    big

    np_max-act-logits · 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
     estekak
    -0.85
    OGND
    -0.64
    reportWebVitals
    -0.63
    rollup
    -0.59
    SpringBootTest
    -0.59
     חיצוניים
    -0.59
    testify
    -0.58
    XtraEditors
    -0.58
     виправивши
    -0.57
    AppMethodBeat
    -0.57
    POSITIVE LOGITS
    !*\
    0.50
    SerializedSize
    0.48
     &___
    0.48
     preſent
    0.46
     production
    0.44
    PDOException
    0.44
    raisemb
    0.43
     paycheck
    0.43
     adjustment
    0.42
     prefent
    0.42
    Activations Density 0.000%

    No Known Activations