© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    energy

    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
    
    -0.72
    tagext
    -0.60
    <?
    -0.59
    +#+
    -0.58
    tagHelper
    -0.56
    DispatchToProps
    -0.55
     AssemblyCulture
    -0.54
    TagHelper
    -0.54
    Tikang
    -0.54
    ween
    -0.52
    POSITIVE LOGITS
     fields
    0.66
    Fields
    0.61
    fields
    0.60
     Fields
    0.60
    FIELDS
    0.59
    intahan
    0.54
     FIELDS
    0.53
     themselves
    0.49
     plage
    0.47
    Updater
    0.46
    Activations Density 0.000%

    No Known Activations