© 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. 0-CLT-HP
    4. 1271
    Prev
    Next
    INDEX
    Explanations

    Emphasis using "THIS"

    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
    ari
    -1.22
    ARI
    -0.73
    ek
    -0.48
     Peoples
    -0.47
    brido
    -0.47
    cee
    -0.47
     are
    -0.46
     this
    -0.46
     resourceCulture
    -0.44
     hit
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.82
    +#+
    0.66
    KELEY
    0.66
    FormTagHelper
    0.65
    Kariera
    0.63
    sterious
    0.62
     pleaſure
    0.62
    مقاله
    0.62
    PageIndex
    0.61
    MigrationBuilder
    0.60
    Activations Density 0.235%

    No Known Activations