© 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. 90984
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    tvguidetime
    -0.58
    ﷺ
    -0.51
    .³
    -0.46
     resourceCulture
    -0.46
     endforeach
    -0.46
    itura
    -0.45
    NOPQRST
    -0.45
    ised
    -0.44
    
    -0.44
    edip
    -0.44
    POSITIVE LOGITS
    IsContent
    0.63
     Normdatei
    0.60
    جغرافيا
    0.56
     Familienname
    0.53
     CascadeType
    0.53
    Халык
    0.52
    hloro
    0.51
    andoah
    0.51
     ddelweddau
    0.50
    обходимо
    0.50
    Activations Density 0.003%

    No Known Activations