© 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. 20-CLT-HP
    4. 74869
    Prev
    Next
    INDEX
    Explanations

    Code/technical snippets

    np_max-act-logits · 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
    formik
    -0.50
     beginnetje
    -0.50
    unhofer
    -0.49
    OrBuilder
    -0.47
     Minang
    -0.46
    άζ
    -0.46
     Lohn
    -0.45
     препратки
    -0.45
    adpleegd
    -0.44
     starfish
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.73
     pulumi
    0.65
    MessageOf
    0.64
     datter
    0.56
    ViewImports
    0.52
    Must
    0.52
    ülle
    0.51
     CreateTagHelper
    0.51
     NUKAT
    0.51
    TagMode
    0.50
    Activations Density 0.001%

    No Known Activations