© 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. 1-CLT-HP
    7. 11411
    Prev
    Next
    INDEX
    Explanations

    mos

    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
    RunWith
    -0.65
     Renew
    -0.60
    Kanpo
    -0.58
    ✨:
    -0.57
    extrême
    -0.55
     fattori
    -0.53
    Rhestr
    -0.53
    RetentionPolicy
    -0.52
    Демографія
    -0.52
    Parcelize
    -0.52
    POSITIVE LOGITS
    ians
    0.63
    ables
    0.60
    observer
    0.55
     Anchorage
    0.53
     Catawiki
    0.53
    ed
    0.52
    edig
    0.52
    iastes
    0.51
    ise
    0.51
    sand
    0.51
    Activations Density 0.027%

    No Known Activations