© 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. 73041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Geplaatst
    -0.56
    ########.
    -0.53
    WEBPACK
    -0.53
    Portale
    -0.51
     Allociné
    -0.49
    RTLD
    -0.49
     sabbia
    -0.49
    UnknownFields
    -0.49
    FieldNumber
    -0.48
     jScrollPane
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.61
    AnchorTagHelper
    0.54
    存于互联网档案馆
    0.52
    IUrlHelper
    0.52
     Soli
    0.49
     density
    0.48
     lenker
    0.48
     Paulina
    0.48
     blindness
    0.47
     Autorizaciones
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.