© 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. 5-CLT-HP
    7. 96122
    Prev
    Next
    INDEX
    Explanations

    zero or division

    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
     ""],
    -0.57
    ValueStyle
    -0.53
     Fib
    -0.53
     Serv
    -0.52
     Shin
    -0.52
    offsetof
    -0.51
     TRIB
    -0.50
    //
    -0.50
     Ear
    -0.49
    AddTagHelper
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.62
     resourceCulture
    0.59
    Diweddarwch
    0.56
     récents
    0.55
     télécommande
    0.54
    stans
    0.51
    couz
    0.51
     charité
    0.51
     nôtre
    0.50
     scorso
    0.50
    Activations Density 0.001%

    No Known Activations