© 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. 71297
    Prev
    Next
    INDEX
    Explanations

    research articles

    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
    prefixer
    -0.56
    EXTERN
    -0.56
     ویکی‌پدیا
    -0.55
    ResponseWriter
    -0.52
    CppMethod
    -0.52
     OnInit
    -0.48
    Referințe
    -0.48
     Licenses
    -0.45
    TemporalType
    -0.44
    ltä
    -0.44
    POSITIVE LOGITS
     Maximum
    0.69
     насељу
    0.68
     maximum
    0.66
    Maximum
    0.66
     neighbor
    0.65
    DockStyle
    0.61
     transfieras
    0.60
    ]<<"
    0.59
     neighbour
    0.59
    maximum
    0.57
    Activations Density 0.001%

    No Known Activations