© 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. 5-CLT-HP
    7. 551
    Prev
    Next
    INDEX
    Explanations

    Identifiers/codes

    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
    GEBURTSDATUM
    -0.69
    Jeografia
    -0.64
    KURZBESCHREIBUNG
    -0.63
    irical
    -0.60
    abestanden
    -0.59
     intptr
    -0.55
    IonicModule
    -0.54
     Réponses
    -0.53
    expandindo
    -0.52
    OfYear
    -0.52
    POSITIVE LOGITS
     vastaan
    0.48
     potuto
    0.47
    &&
    0.44
     ModelExpression
    0.44
    kembangan
    0.44
    junit
    0.44
     diputados
    0.43
     marah
    0.43
    יתוף
    0.43
     förb
    0.43
    Activations Density 0.008%

    No Known Activations