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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12761
    Prev
    Next
    INDEX
    Explanations

    Code and random text

    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
     surla
    -0.79
    Erreferentziak
    -0.72
    ագրություններ
    -0.66
    XtraReports
    -0.63
    íncia
    -0.63
     Normdatei
    -0.62
    RenderAtEndOf
    -0.59
    锈钢
    -0.59
    Посилання
    -0.58
    AlterField
    -0.57
    POSITIVE LOGITS
     Staff
    0.44
    marginHorizontal
    0.42
     put
    0.42
    鰭
    0.40
     AMEN
    0.39
    rospy
    0.38
    atr
    0.38
     préc
    0.37
     STAFF
    0.36
    Traducción
    0.36
    Activations Density 0.005%

    No Known Activations