© 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. 43505
    Prev
    Next
    INDEX
    Explanations

    methodology

    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
    Meeting
    -0.71
     meeting
    -0.66
     ContentValues
    -0.65
    writeFieldEnd
    -0.65
     Fund
    -0.64
    himovic
    -0.64
     AttributeSet
    -0.63
    meeting
    -0.63
    yntaxException
    -0.60
     Meeting
    -0.60
    POSITIVE LOGITS
     propOrder
    0.55
     esterni
    0.52
     termica
    0.50
     prisonniers
    0.50
     cadeia
    0.49
     riduzione
    0.47
    strptime
    0.46
     stessa
    0.45
    îtra
    0.45
     vicenda
    0.44
    Activations Density 0.048%

    No Known Activations