© 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. 5-CLT-HP
    7. 4008
    Prev
    Next
    INDEX
    Explanations

    ing

    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
     the
    -1.17
     a
    -1.02
     an
    -0.88
     some
    -0.84
     various
    -0.81
     certain
    -0.81
     its
    -0.77
     Wiktionnaire
    -0.74
     significant
    -0.72
     considerable
    -0.70
    POSITIVE LOGITS
    ly
    0.47
     şekilde
    0.45
    yet
    0.36
    WebServlet
    0.36
     вони
    0.36
    they
    0.35
     määrä
    0.35
     вона
    0.34
    BoxShadow
    0.34
    she
    0.33
    Activations Density 0.015%

    No Known Activations