© 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. 93630
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Bril
    -0.55
     بيها
    -0.50
    ỡng
    -0.47
    LabelTagHelper
    -0.47
     acorns
    -0.45
    omány
    -0.44
    excellents
    -0.44
    ագրություններ
    -0.44
     recupera
    -0.44
     récon
    -0.43
    POSITIVE LOGITS
    outState
    0.63
    PRNewswire
    0.58
    endsection
    0.57
     případě
    0.57
    CreateMap
    0.57
     виправивши
    0.56
    MergeFrom
    0.52
    äus
    0.49
    digkeit
    0.49
     protoimpl
    0.49
    Activations Density 0.003%

    No Known Activations