© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 852
    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
    ulaski
    -0.51
    salms
    -0.49
     argint
    -0.48
     dianteiro
    -0.47
     poésie
    -0.46
    towany
    -0.46
     malheur
    -0.45
     favors
    -0.45
    Animations
    -0.45
    gorithm
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.84
    rrggbb
    0.66
    VIAF
    0.66
     незавершена
    0.65
    
    0.65
    Portail
    0.62
    psack
    0.59
     بيها
    0.59
    ChildScrollView
    0.59
    новништво
    0.57
    Activations Density 0.031%

    No Known Activations