© 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. 20-CLT-HP
    7. 77907
    Prev
    Next
    INDEX
    Explanations

    Stro

    np_max-act-logits · 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
     ويكيپيديا
    -0.66
    ItemBackground
    -0.65
     Italijanski
    -0.65
    MessageOf
    -0.64
    AndEndTag
    -0.63
     Administrativna
    -0.63
    UnsafeEnabled
    -0.63
    invokeLater
    -0.60
     незавершена
    -0.60
     disambiguazione
    -0.60
    POSITIVE LOGITS
    ats
    0.47
    atsen
    0.42
    guten
    0.41
    født
    0.40
    ikia
    0.40
    arie
    0.39
     per
    0.39
    ts
    0.38
    upat
    0.38
    okie
    0.38
    Activations Density 0.002%

    No Known Activations