© 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. 1-CLT-HP
    7. 15318
    Prev
    Next
    INDEX
    Explanations

    it

    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
    RenderAtEndOf
    -0.78
    UserScript
    -0.71
    ffindor
    -0.69
     betweenstory
    -0.67
    клопе
    -0.65
    endcsname
    -0.65
    iecie
    -0.64
    endphp
    -0.64
    ſelf
    -0.63
    ]='\
    -0.62
    POSITIVE LOGITS
     under
    0.45
     promotes
    0.43
    WriteTagHelper
    0.43
     brings
    0.41
     applies
    0.39
     helps
    0.39
     form
    0.39
     offers
    0.38
     CreateTagHelper
    0.38
     contributes
    0.37
    Activations Density 0.007%

    No Known Activations