© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95606
    Prev
    Next
    INDEX
    Explanations

    housing and interiors

    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
    Negative Logits
    aarrggbb
    -0.99
    ⓧ
    -0.91
    DoubleQuotes
    -0.81
    +#+#
    -0.77
    astéro
    -0.76
    Gweler
    -0.73
    featureID
    -0.73
    MessageTagHelper
    -0.71
     ProtoMessage
    -0.71
    省市镇
    -0.69
    POSITIVE LOGITS
    der
    0.51
     ")"
    0.45
    ry
    0.43
    )++;
    0.43
     simulation
    0.42
     so
    0.41
     ')'
    0.40
    quoi
    0.40
     document
    0.39
    olding
    0.39
    Activations Density 0.055%

    No Known Activations