© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1048
    Prev
    Next
    INDEX
    Explanations

    bank

    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
     سكانية
    -0.86
     betweenstory
    -0.85
     transférez
    -0.80
     Efq
    -0.79
    Hentet
    -0.78
     utafitiHapana
    -0.76
     transfieras
    -0.74
    mogat
    -0.73
    ibouti
    -0.73
     mxArray
    -0.73
    POSITIVE LOGITS
    ing
    0.69
    e
    0.53
    tant
    0.50
    ци
    0.48
    hila
    0.46
    ING
    0.45
    中
    0.43
    ace
    0.43
    helle
    0.43
    家
    0.43
    Activations Density 0.135%

    No Known Activations