© 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. 5373
    Prev
    Next
    INDEX
    Explanations

    nutrition

    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
    expandindo
    -0.60
     inom
    -0.50
    mtrl
    -0.46
     مرئيه
    -0.46
    อา
    -0.46
     civil
    -0.46
    Tikang
    -0.44
    itschrift
    -0.44
    數
    -0.44
    SerializedSize
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.77
     initComponents
    0.66
     autorytatywna
    0.65
    enseignements
    0.60
     betweenstory
    0.57
     Houſe
    0.57
     houſe
    0.57
     whiteColor
    0.57
    ſelf
    0.56
    ſelves
    0.54
    Activations Density 0.000%

    No Known Activations