© 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. 5-CLT-HP
    7. 96539
    Prev
    Next
    INDEX
    Explanations

    statistics and dates

    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
    ViewFeatures
    -0.68
    Portail
    -0.64
    GOTREF
    -0.56
    "]));
    -0.56
     AssemblyCulture
    -0.55
    ✨:
    -0.53
    évaluateur
    -0.53
    VolleyError
    -0.53
    LLAB
    -0.53
    TagHelper
    -0.52
    POSITIVE LOGITS
     (
    0.68
    liceerd
    0.63
     British
    0.57
     Brits
    0.56
     (£
    0.56
    StructEnd
    0.56
     Britons
    0.53
     a
    0.52
     top
    0.51
     Force
    0.51
    Activations Density 0.001%

    No Known Activations