© 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. 0-CLT-HP
    7. 94575
    Prev
    Next
    INDEX
    Explanations

    beaches

    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
     avoient
    -0.88
     prisonniers
    -0.88
     déput
    -0.84
    SharedDtor
    -0.82
     confronti
    -0.80
     cérami
    -0.78
     météo
    -0.77
     fumée
    -0.75
     bonté
    -0.75
    서는
    -0.75
    POSITIVE LOGITS
     tri
    0.57
     cre
    0.56
     multi
    0.54
     inter
    0.54
     land
    0.54
     ter
    0.51
     cic
    0.50
     Tri
    0.49
     gla
    0.49
     things
    0.47
    Activations Density 0.107%

    No Known Activations