© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13724
    Prev
    Next
    INDEX
    Explanations

    brevity/summaries

    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
     Baumann
    -0.46
     Waray
    -0.45
    HCM
    -0.43
    ulink
    -0.43
     Wiktionnaire
    -0.42
     flocks
    -0.42
    geführten
    -0.42
     suck
    -0.41
     sucking
    -0.41
    veness
    -0.41
    POSITIVE LOGITS
    rungsseite
    1.22
    RenderAtEndOf
    0.88
     שוליים
    0.84
    Personendaten
    0.78
    CodedInputStream
    0.76
    IUrlHelper
    0.72
    DeleteBehavior
    0.70
    NameInMap
    0.69
     ExecuteAsync
    0.69
     disambiguazione
    0.68
    Activations Density 0.019%

    No Known Activations