© 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. 90479
    Prev
    Next
    INDEX
    Explanations

    star

    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
     star
    -1.37
     bird
    -1.16
    bird
    -1.02
     stars
    -0.97
     Star
    -0.94
    star
    -0.93
     Bird
    -0.93
    Bird
    -0.91
     STAR
    -0.88
    BIRD
    -0.87
    POSITIVE LOGITS
    Gön
    0.57
    kháu
    0.57
    PyExc
    0.56
     pinulongan
    0.56
    MigrationBuilder
    0.53
    esez
    0.53
    انجليز
    0.52
     '\\;'
    0.50
    oredCriteria
    0.50
     invari
    0.49
    Activations Density 0.187%

    No Known Activations