© 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. 95750
    Prev
    Next
    INDEX
    Explanations

    Guidance/journey

    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
     to
    -0.63
    idosis
    -0.57
    )}(\
    -0.54
    oplayer
    -0.53
     }}(\
    -0.53
    InjectAttribute
    -0.52
    TimeTo
    -0.52
    MessageTagHelper
    -0.52
    asures
    -0.50
    naments
    -0.50
    POSITIVE LOGITS
    TypedDataSet
    0.81
     ujednoznacz
    0.77
    fjspx
    0.75
    脚注の使い方
    0.66
    AndEndTag
    0.65
    smithy
    0.63
     autorytatywna
    0.61
    RegistryLite
    0.59
    IntoConstraints
    0.59
     ExecuteAsync
    0.58
    Activations Density 0.033%

    No Known Activations