© 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. 10096
    Prev
    Next
    INDEX
    Explanations

    semiconductors and devices

    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
     getopt
    -0.58
     otomatig
    -0.56
    <bos>
    -0.53
     FetchType
    -0.53
    Пра
    -0.51
     Мексичка
    -0.51
    ########.
    -0.46
     proté
    -0.46
     Referential
    -0.44
    acl
    -0.44
    POSITIVE LOGITS
    存于互联网档案馆
    0.68
     الرياضيه
    0.66
     nonUne
    0.64
    ipto
    0.62
    日閲覧
    0.60
     Normdatei
    0.59
     дописавши
    0.59
     leçon
    0.58
    enderror
    0.58
    μως
    0.57
    Activations Density 0.157%

    No Known Activations