© 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. 71551
    Prev
    Next
    INDEX
    Explanations

    Odkazy

    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
    Negative Logits
    __':
    -0.63
    ScopeManager
    -0.63
     stomat
    -0.63
     SafeMath
    -0.62
     Gears
    -0.62
    исленность
    -0.62
     Geophys
    -0.61
    __":
    -0.60
    enderror
    -0.60
    __':
    -0.59
    POSITIVE LOGITS
    Odkazy
    0.49
    bis
    0.43
     ostavi
    0.41
     ul
    0.40
     bis
    0.40
    藍
    0.40
     disambiguazione
    0.39
     Pandey
    0.39
    anit
    0.38
    DebuggerNonUser
    0.38
    Activations Density 0.002%

    No Known Activations