© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98095
    Prev
    Next
    INDEX
    Explanations

    sharing

    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
     članak
    -0.73
    Попис
    -0.70
    +#+#
    -0.66
    şiv
    -0.65
    WebServlet
    -0.65
    TagMode
    -0.65
    тьяна
    -0.64
     NgModule
    -0.62
     Winaray
    -0.62
     ArrayAdapter
    -0.61
    POSITIVE LOGITS
     with
    0.63
     about
    0.62
     little
    0.51
     these
    0.49
     its
    0.49
     no
    0.47
     long
    0.46
     it
    0.45
    mb
    0.44
    amb
    0.43
    Activations Density 0.002%

    No Known Activations