© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10050
    Prev
    Next
    INDEX
    Explanations

    rons

    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
     noDo
    -0.52
     Ensign
    -0.50
    SuspendLayout
    -0.49
    OCCURRED
    -0.49
    kloped
    -0.48
     Mascara
    -0.48
     predictability
    -0.48
     swift
    -0.48
    AddRange
    -0.47
     schnellen
    -0.47
    POSITIVE LOGITS
    Rüyada
    0.65
    исленность
    0.57
     переписи
    0.55
    ErrUnexpectedEOF
    0.51
    !*\
    0.49
     MainAxisSize
    0.49
    TagMode
    0.47
    Amicalement
    0.47
    +#+
    0.46
    findpost
    0.46
    Activations Density 0.063%

    No Known Activations