© 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. 0-CLT-HP
    7. 1744
    Prev
    Next
    INDEX
    Explanations

    homes

    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
     homes
    -2.03
     HOMES
    -1.55
     houses
    -1.53
     Homes
    -1.52
    homes
    -1.52
    Homes
    -1.37
     households
    -1.35
     Houses
    -1.22
    houses
    -1.20
     residences
    -1.19
    POSITIVE LOGITS
     and
    0.57
     in
    0.52
     tiba
    0.50
    .
    0.48
    ,
    0.47
    kin
    0.45
    ’
    0.45
    mith
    0.44
     are
    0.42
    ide
    0.42
    Activations Density 0.037%

    No Known Activations