© 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. 93902
    Prev
    Next
    INDEX
    Explanations

    :

    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
    awtextra
    -0.76
     disambiguazione
    -0.66
    IntoConstraints
    -0.63
     صوتيه
    -0.61
    IMPORTED
    -0.60
    __*/
    -0.59
     tịch
    -0.59
    GIVEREF
    -0.57
     beaten
    -0.57
    ยม
    -0.57
    POSITIVE LOGITS
    èdia
    0.50
     getResource
    0.42
    Rè
    0.41
    WriteBarrier
    0.40
    ItemBackground
    0.40
    XmlType
    0.40
     punten
    0.40
    ashqai
    0.40
    And
    0.39
    CPtr
    0.39
    Activations Density 0.001%

    No Known Activations