© 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. 0-CLT-HP
    7. 41585
    Prev
    Next
    INDEX
    Explanations

    kinetics

    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
     Min
    -0.56
     Guiding
    -0.54
    Min
    -0.50
    Gu
    -0.46
     Bob
    -0.44
    RAC
    -0.43
     gesch
    -0.42
     sagen
    -0.41
     minne
    -0.41
     MyBatis
    -0.41
    POSITIVE LOGITS
     propOrder
    0.88
    ukone
    0.68
    ayaquil
    0.67
     ujednoznacz
    0.66
    eafter
    0.65
    WebControls
    0.65
     SqlDbType
    0.60
    ed
    0.60
    dient
    0.60
    rophes
    0.59
    Activations Density 0.054%

    No Known Activations