© 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. 77056
    Prev
    Next
    INDEX
    Explanations

    Random topics

    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
     sèche
    -0.70
    Tikang
    -0.68
     unknownFields
    -0.66
     незавершена
    -0.65
    Erreferentziak
    -0.60
     متعلقه
    -0.59
     Signalez
    -0.59
     inoxydable
    -0.58
    %</
    -0.58
     CreateTagHelper
    -0.57
    POSITIVE LOGITS
    WebVitals
    0.55
    #+#
    0.51
     Spitz
    0.47
     paste
    0.47
     Verarbeitung
    0.46
    SharedModule
    0.44
     diary
    0.44
    eleste
    0.44
    fml
    0.42
     motherhood
    0.41
    Activations Density 0.003%

    No Known Activations