© 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. 43654
    Prev
    Next
    INDEX
    Explanations

    dad

    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
     fathers
    -1.17
     dads
    -1.03
     mothers
    -0.94
     husbands
    -0.86
    Dad
    -0.84
    parents
    -0.81
     Dad
    -0.81
     dad
    -0.78
    dad
    -0.77
     Fathers
    -0.76
    POSITIVE LOGITS
    tagHelperRunner
    0.57
    reactstrap
    0.56
    angliski
    0.51
    BeginContext
    0.49
    oa
    0.46
    ую
    0.46
    )^{
    0.45
    o
    0.45
     />\
    0.44
    +"\
    0.43
    Activations Density 1.412%

    No Known Activations