© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76575
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · 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
    Сюжет
    -0.61
    agers
    -0.60
    FieldBuilder
    -0.59
     createState
    -0.58
    ager
    -0.56
     Silurian
    -0.54
     createContext
    -0.53
     שוליים
    -0.53
    aging
    -0.52
    Попис
    -0.52
    POSITIVE LOGITS
    IContainer
    0.52
     AspNetCore
    0.48
     judiciales
    0.45
     Roskov
    0.45
     telefónica
    0.44
    empereur
    0.44
     responsabilité
    0.43
     indipendente
    0.42
    Hentet
    0.41
     judiciaire
    0.41
    Activations Density 0.008%

    No Known Activations