© 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. 93054
    Prev
    Next
    INDEX
    Explanations

    comparisons of quality

    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
    )$}
    -0.64
     EconPapers
    -0.63
     wikipagina
    -0.60
     esternos
    -0.57
    Datuak
    -0.57
    troppo
    -0.57
    újo
    -0.56
    CharacterOffset
    -0.56
     resourceCulture
    -0.56
    wareness
    -0.56
    POSITIVE LOGITS
     to
    0.92
    WriteTagHelper
    0.57
     <<<<<<<<<<<<<<
    0.55
     vnto
    0.52
     doInBackground
    0.49
    basicConfig
    0.48
     in
    0.48
    IGraphics
    0.46
     suited
    0.44
    VIAF
    0.44
    Activations Density 0.001%

    No Known Activations