© 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. 4171
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Keeps
    -0.80
     maintaining
    -0.79
     maintain
    -0.77
     сохра
    -0.76
     Maintaining
    -0.72
     keeps
    -0.71
     maintained
    -0.71
     keeping
    -0.69
     Keeping
    -0.69
    Keeps
    -0.68
    POSITIVE LOGITS
     CreateTagHelper
    1.14
    MLLoader
    0.79
    OGND
    0.76
     Efq
    0.75
     Савезне
    0.75
    TypedDataSet
    0.74
     myſelf
    0.73
     kasarigan
    0.72
    ſelf
    0.71
    complexContent
    0.71
    Activations Density 0.025%

    No Known Activations