© 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. 0-CLT-HP
    7. 97530
    Prev
    Next
    INDEX
    Explanations

    Philharmonic

    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
    inesis
    -0.75
    gang
    -0.63
     Pren
    -0.61
     Lyt
    -0.59
    KURZBESCHREIBUNG
    -0.55
    ences
    -0.52
     whor
    -0.50
    θεια
    -0.50
     kasarigan
    -0.49
    aság
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.74
    HomeAsUpEnabled
    0.62
    contentLoaded
    0.61
    CloseOperation
    0.60
    SharedDtor
    0.59
    SizeF
    0.59
    DeleteBehavior
    0.57
    AntiForgeryToken
    0.57
    Clik
    0.56
    Pranala
    0.53
    Activations Density 0.130%

    No Known Activations