© 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. 4-CLT-HP
    7. 4331
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ंदीखरीदारी
    -0.70
    rrggbb
    -0.57
    AnchorStyles
    -0.56
     AttributeSet
    -0.56
    #
    -0.56
    ⓧ
    -0.56
     kasarigan
    -0.54
    раздо
    -0.53
    SuccessListener
    -0.52
     تضيفلها
    -0.51
    POSITIVE LOGITS
    市镇
    0.62
    roud
    0.58
    țiuni
    0.57
    kehrt
    0.56
     aran
    0.55
    kembang
    0.52
     getAddress
    0.51
    adjusted
    0.51
     aéri
    0.49
    onics
    0.49
    Activations Density 0.001%

    No Known Activations