© 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. 5-CLT-HP
    7. 97954
    Prev
    Next
    INDEX
    Explanations

    Historical periods

    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
    arXiv
    -0.47
     castelo
    -0.46
     matéria
    -0.44
     vermelhas
    -0.43
    .
    -0.42
     entanto
    -0.42
    explique
    -0.41
     siRNA
    -0.40
     térmica
    -0.40
    misu
    -0.38
    POSITIVE LOGITS
    webElementXpaths
    0.93
     beginnetje
    0.68
     Meksiku
    0.66
     autorytatywna
    0.64
     numerus
    0.63
    
    0.62
     invokingState
    0.61
    AddTagHelper
    0.60
     decades
    0.60
    undred
    0.58
    Activations Density 0.001%

    No Known Activations