© 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. 14136
    Prev
    Next
    INDEX
    Explanations

    piece/part

    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
     Dostupné
    -0.43
     U
    -0.41
    水中
    -0.39
    цездатний
    -0.39
    ★★★★★
    -0.39
     Tw
    -0.38
    typeof
    -0.37
    一樣
    -0.36
     Luk
    -0.36
    nowrap
    -0.36
    POSITIVE LOGITS
    ParallelGroup
    0.71
    itinéraire
    0.66
     BoxFit
    0.66
    ########.
    0.65
    netje
    0.64
     BoxDecoration
    0.63
    seamnă
    0.63
     enfans
    0.61
     ujednoznacz
    0.61
     antaranya
    0.61
    Activations Density 0.030%

    No Known Activations