© 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. 5-CLT-HP
    4. 2816
    Prev
    Next
    INDEX
    Explanations

    of

    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
     force
    -0.58
     error
    -0.57
     passion
    -0.53
     care
    -0.52
     sing
    -0.51
     power
    -0.51
     study
    -0.51
     
    -0.51
     live
    -0.51
     fix
    -0.51
    POSITIVE LOGITS
    GEBURTSDATUM
    1.00
    tagHelperRunner
    0.95
    parsedMessage
    0.88
    Datuak
    0.85
    AutoScaleMode
    0.84
     виправивши
    0.84
     HttpNotFound
    0.84
     démocr
    0.76
     سكانية
    0.69
    CloseOperation
    0.68
    Activations Density 0.000%

    No Known Activations