© 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. 5-CLT-HP
    7. 94364
    Prev
    Next
    INDEX
    Explanations

    code/programming environment

    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
     skär
    -0.57
    AutoScaleMode
    -0.56
     <>",
    -0.53
     Esco
    -0.51
     Independencia
    -0.50
    uste
    -0.50
     pitié
    -0.50
    chere
    -0.49
     Yates
    -0.49
    eronau
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.65
    ThroughAttribute
    0.60
    VIAF
    0.51
     linkovi
    0.51
    epik
    0.49
    AMC
    0.48
    itattu
    0.47
    Doh
    0.47
    milli
    0.46
    drip
    0.45
    Activations Density 0.001%

    No Known Activations