© 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. 91190
    Prev
    Next
    INDEX
    Explanations

    do

    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
    bootstrapcdn
    -0.60
    InitStruct
    -0.59
    rungsseite
    -0.58
     RouterModule
    -0.56
    IUrlHelper
    -0.54
    Արտաքին
    -0.53
     Smarty
    -0.52
    +#+#
    -0.51
    bcryptjs
    -0.51
    Havolalar
    -0.50
    POSITIVE LOGITS
     MainAxisSize
    0.64
    makeText
    0.60
    PageIndex
    0.59
     Perché
    0.57
    IBar
    0.55
    ناك
    0.54
     stessi
    0.52
    mobileqq
    0.52
     disponibilités
    0.52
    ]")]
    0.50
    Activations Density 0.067%

    No Known Activations