© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90902
    Prev
    Next
    INDEX
    Explanations

    values

    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
    Negative Logits
     perdidos
    -0.69
     المعيارى
    -0.68
     vendu
    -0.60
     proposée
    -0.59
     requerida
    -0.58
     gantung
    -0.58
     proposées
    -0.57
     compartido
    -0.56
    reszcie
    -0.56
     deseado
    -0.55
    POSITIVE LOGITS
    LookAnd
    0.59
     direct
    0.53
    ectoria
    0.53
    Derp
    0.53
     ***!
    0.52
    "}")
    0.51
     prompt
    0.50
    colorPrimary
    0.47
     maintaining
    0.47
    AVOR
    0.47
    Activations Density 0.001%

    No Known Activations