© 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. 20-CLT-HP
    7. 72207
    Prev
    Next
    INDEX
    Explanations

    Marketing and news articles

    np_max-act-logits · 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
    ValueStyle
    -0.79
    NameInMap
    -0.73
    InjectAttribute
    -0.65
    Geplaatst
    -0.62
     bide
    -0.61
     CreateTagHelper
    -0.57
    WithMany
    -0.57
    fortawesome
    -0.56
    Clik
    -0.56
     <<<<<<<<<<<<<<
    -0.56
    POSITIVE LOGITS
     Driving
    0.71
    Driving
    0.70
     driving
    0.69
    driving
    0.65
     fédé
    0.58
     volna
    0.53
     vägen
    0.52
     vectorielle
    0.52
     otomatig
    0.52
     étoient
    0.51
    Activations Density 0.000%

    No Known Activations