© 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. 4-CLT-HP
    7. 2343
    Prev
    Next
    INDEX
    Explanations

    technical/specific language

    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
    toarele
    -0.48
    toare
    -0.47
    SequentialGroup
    -0.45
     Jann
    -0.45
    Literatuur
    -0.44
    ControllerTest
    -0.43
     τον
    -0.41
    Viited
    -0.41
    Atsauces
    -0.41
     '\\;'
    -0.40
    POSITIVE LOGITS
    DECREF
    0.63
    DataContract
    0.60
    esez
    0.57
    ächst
    0.56
     defaultstate
    0.56
     arşivlendi
    0.55
    __":
    0.55
     Bue
    0.55
     XCTest
    0.54
    contentLoaded
    0.53
    Activations Density 0.001%

    No Known Activations