© 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. 5144
    Prev
    Next
    INDEX
    Explanations

    natural world

    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
    Chham
    -0.55
     Paglinawan
    -0.55
    RenderAtEndOf
    -0.53
    enfone
    -0.49
    таратура
    -0.48
    
    -0.47
     MainAxisSize
    -0.46
    becue
    -0.46
    WebVitals
    -0.45
     оригіналу
    -0.43
    POSITIVE LOGITS
    +#+#
    0.79
    LookAnd
    0.69
     виправивши
    0.55
     brach
    0.52
    AndEndTag
    0.52
    GEBURTSDATUM
    0.52
     Ake
    0.52
     stacks
    0.52
     Meksiku
    0.51
     OMITBAD
    0.51
    Activations Density 0.001%

    No Known Activations