© 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. 1-CLT-HP
    7. 8849
    Prev
    Next
    INDEX
    Explanations

    line

    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
    atimes
    -0.66
    antMatchers
    -0.60
    NameInMap
    -0.60
    zczegól
    -0.59
    AddHtmlAttribute
    -0.58
    slidesToShow
    -0.56
    mag
    -0.52
     Exactos
    -0.51
    Coordenadas
    -0.50
    UnsafeEnabled
    -0.50
    POSITIVE LOGITS
    SharedCtor
    0.64
    //{
    0.57
    zdo
    0.56
     estekak
    0.54
    ougou
    0.50
    isela
    0.49
    ualaikum
    0.49
    NewUrlParser
    0.48
    __':
    0.48
     تانيه
    0.48
    Activations Density 0.036%

    No Known Activations