© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96133
    Prev
    Next
    INDEX
    Explanations

    question

    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
    AddHtmlAttribute
    -0.46
    getDescriptor
    -0.45
    lada
    -0.43
     Aero
    -0.43
     reservoir
    -0.42
     ytter
    -0.41
     centrif
    -0.40
    kyl
    -0.39
    heel
    -0.39
    opress
    -0.38
    POSITIVE LOGITS
     whether
    0.71
    whether
    0.69
     why
    0.65
    例文帳に追加
    0.65
     Whether
    0.65
     convaincre
    0.63
     WHETHER
    0.62
     what
    0.60
     apakah
    0.59
    Whether
    0.58
    Activations Density 0.005%

    No Known Activations