© 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. 5958
    Prev
    Next
    INDEX
    Explanations

    of for

    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
    şiv
    -0.67
    <bos>
    -0.66
     AssemblyCulture
    -0.63
     helping
    -0.60
    helping
    -0.60
     ensuring
    -0.59
    FormTagHelper
    -0.59
     AssemblyProduct
    -0.58
     discovering
    -0.53
     mejorando
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.63
    extAlignment
    0.63
    ksikon
    0.60
     unexplained
    0.55
    atimes
    0.53
     persistent
    0.52
     nakalista
    0.52
     disobedience
    0.50
    plained
    0.50
     infertility
    0.50
    Activations Density 0.001%

    No Known Activations