© 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. 38470
    Prev
    Next
    INDEX
    Explanations

    at, in

    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
    in
    -0.93
    at
    -0.84
     poussière
    -0.65
     poitrine
    -0.63
     douleur
    -0.60
     revés
    -0.60
     مشين
    -0.60
    inac
    -0.60
     défaite
    -0.57
     dignité
    -0.57
    POSITIVE LOGITS
     the
    0.85
     an
    0.71
     a
    0.67
     relation
    0.66
     terms
    0.65
     our
    0.59
    ting
    0.59
     their
    0.57
    ned
    0.57
     conjunction
    0.54
    Activations Density 0.057%

    No Known Activations