© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38369
    Prev
    Next
    INDEX
    Explanations

    tale

    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
     MainAxisSize
    -0.83
    s
    -0.75
     Players
    -0.75
    IContainer
    -0.75
    TypedDataSet
    -0.73
    Personensuche
    -0.72
     deleting
    -0.68
    e
    -0.68
    Players
    -0.68
    WebVitals
    -0.68
    POSITIVE LOGITS
     referenties
    0.50
     вот
    0.45
    neum
    0.45
     caras
    0.43
     open
    0.42
    anius
    0.42
     кампа
    0.41
     support
    0.40
    सन्दर्भ
    0.40
     Umum
    0.38
    Activations Density 0.043%

    No Known Activations