© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    part

    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
    utilisons
    -0.67
    protoimpl
    -0.65
     lenker
    -0.64
     Administrativna
    -0.61
     Wicidata
    -0.59
    Diweddarwch
    -0.58
     دیکھیے
    -0.57
    ensement
    -0.56
     étend
    -0.55
     Meilleures
    -0.55
    POSITIVE LOGITS
     why
    0.65
    ibol
    0.53
     a
    0.53
     JAXBElement
    0.52
     HasFactory
    0.51
    SqlClient
    0.50
     Why
    0.48
     luck
    0.47
    NameValuePair
    0.46
     IBOutlet
    0.46
    Activations Density 0.002%

    No Known Activations