© 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. 1-CLT-HP
    7. 9017
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ERI
    -0.50
     vague
    -0.45
     novelty
    -0.45
     vý
    -0.44
     structural
    -0.43
    uhn
    -0.41
    Saludos
    -0.41
     aux
    -0.41
    NOST
    -0.41
     coverage
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.98
     AssemblyCulture
    0.92
    tagHelperRunner
    0.84
     CreateTagHelper
    0.79
     resourceCulture
    0.78
    Tikang
    0.76
    ChildScrollView
    0.75
     cesse
    0.73
    DockStyle
    0.72
    AndEndTag
    0.70
    Activations Density 0.013%

    No Known Activations