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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45823
    Prev
    Next
    INDEX
    Explanations

    medical topics

    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
     Grecs
    -0.68
    Garantie
    -0.59
    amaño
    -0.56
     Gole
    -0.56
     Cæsar
    -0.56
    gisayar
    -0.55
     Camilo
    -0.55
     Accueil
    -0.55
     Constantinople
    -0.54
     sleeve
    -0.54
    POSITIVE LOGITS
     quen
    0.57
    ArgsConstructor
    0.53
     "..\..\
    0.50
     Италијани
    0.50
    CppCodeGen
    0.47
    >",
    0.46
    SourceChecksum
    0.45
    ConstraintMaker
    0.43
    PickerController
    0.42
    Anhalt
    0.41
    Activations Density 0.056%

    No Known Activations