Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12781
    Prev
    Next
    INDEX
    Explanations

    ulets

    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
     invokingState
    -0.79
    Harmful
    -0.77
     BrowserModule
    -0.76
    migrationBuilder
    -0.74
    adə
    -0.73
     Harmful
    -0.72
     pinulongan
    -0.72
    Rujuakan
    -0.72
    +#+#
    -0.71
     PyLong
    -0.71
    POSITIVE LOGITS
    pośred
    0.55
     себе
    0.51
     Release
    0.42
    zeka
    0.42
     espejo
    0.42
    atangan
    0.42
    isClosed
    0.42
     Game
    0.42
     dön
    0.41
     streamline
    0.41
    Activations Density 0.022%

    No Known Activations