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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93177
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific content

    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
     WE
    -0.52
     JpaRepository
    -0.50
     Adel
    -0.49
    cill
    -0.47
     Hel
    -0.47
    ferrer
    -0.46
     talál
    -0.45
     Pharmacol
    -0.45
     Fah
    -0.45
    dataTable
    -0.44
    POSITIVE LOGITS
    utenant
    0.62
    Geplaatst
    0.60
    LookAnd
    0.59
     Offisielt
    0.59
     AppColors
    0.57
    rungsseite
    0.56
    ttino
    0.56
    ษา
    0.56
     Савезне
    0.55
    complexContent
    0.55
    Activations Density 1.589%

    No Known Activations