© 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. 5-CLT-HP
    7. 92724
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    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
     nữa
    -0.55
    ppure
    -0.47
    HtmlAttribute
    -0.47
    Even
    -0.47
     even
    -0.46
    How
    -0.45
    is
    -0.45
    AutoScale
    -0.44
     пожалуйста
    -0.44
     البته
    -0.43
    POSITIVE LOGITS
    writeFieldEnd
    0.88
    OGND
    0.77
    GOTREF
    0.75
    IVEREF
    0.74
     getItemId
    0.72
    adpleegd
    0.70
    MLLoader
    0.70
     المعيارى
    0.69
    ########.
    0.69
     Италијани
    0.68
    Activations Density 0.038%

    No Known Activations