© 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. 92638
    Prev
    Next
    INDEX
    Explanations

    outside

    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
     outside
    -1.88
    Outside
    -1.70
    outside
    -1.70
     Outside
    -1.56
     OUTSIDE
    -1.39
     utanför
    -1.20
     buiten
    -1.20
     extérieurs
    -1.17
     extérieures
    -1.16
     extérieur
    -1.16
    POSITIVE LOGITS
     the
    0.96
     of
    0.88
     their
    0.74
     its
    0.73
     your
    0.68
     Ceramby
    0.62
     Europe
    0.60
     our
    0.60
     Asia
    0.59
     Thailand
    0.59
    Activations Density 0.042%

    No Known Activations