© 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. 92835
    Prev
    Next
    INDEX
    Explanations

    wandering

    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
    RenderAtEndOf
    -0.66
     AppColors
    -0.57
     saites
    -0.55
    olkata
    -0.54
    phosa
    -0.52
    tagHelper
    -0.49
    scientific
    -0.49
     biologists
    -0.48
     minds
    -0.48
     Fok
    -0.48
    POSITIVE LOGITS
     Roskov
    0.73
     <=",
    0.58
    SequentialGroup
    0.57
    сшта
    0.57
    igate
    0.53
     arbete
    0.52
     يتيمه
    0.51
    Erstellt
    0.50
    godic
    0.50
     EnglishChoose
    0.50
    Activations Density 0.000%

    No Known Activations