© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94302
    Prev
    Next
    INDEX
    Explanations

    Physics/Math principles

    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
     themſelves
    -0.91
    LookAnd
    -0.90
     Efq
    -0.87
     Audiodateien
    -0.86
     Meksiku
    -0.83
     resourceCulture
    -0.82
     <>",
    -0.81
    ]")]
    -0.80
     ModelRenderer
    -0.80
     AssemblyProduct
    -0.79
    POSITIVE LOGITS
    /
    0.56
     /
    0.47
    of
    0.40
     will
    0.37
     проводится
    0.37
    has
    0.35
     or
    0.35
     A
    0.35
    A
    0.35
    ea
    0.35
    Activations Density 0.010%

    No Known Activations