© 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. 0-CLT-HP
    7. 95573
    Prev
    Next
    INDEX
    Explanations

    InstanceState

    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
     חיצוניים
    -0.56
     CreateTagHelper
    -0.54
     alcuna
    -0.49
    ГЛА
    -0.45
     and
    -0.44
    tahankan
    -0.44
     access
    -0.43
     acesso
    -0.42
    eax
    -0.42
     limão
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.79
     otomatig
    0.79
     ***!
    0.70
     CONSE
    0.69
    cèse
    0.68
     conso
    0.68
     ſeveral
    0.68
    bolista
    0.66
     ſche
    0.66
     Monfieur
    0.66
    Activations Density 0.188%

    No Known Activations