© 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. 2155
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Enix
    -0.47
    ומת
    -0.46
    leston
    -0.41
    ForUser
    -0.41
    apunov
    -0.40
    Vital
    -0.40
    ureusement
    -0.40
    Absolute
    -0.40
    比如
    -0.39
     Colony
    -0.39
    POSITIVE LOGITS
    kháu
    0.69
    NameInMap
    0.67
    EndTag
    0.65
    Дереккөздер
    0.60
    parsedMessage
    0.60
    themselves
    0.58
    Jereo
    0.58
    ItemBackground
    0.57
    }`).
    0.57
    AddTagHelper
    0.57
    Activations Density 0.002%

    No Known Activations