© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76402
    Prev
    Next
    INDEX
    Explanations

    not

    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
    expandindo
    -0.95
     gynhyrchwyd
    -0.92
    :✨
    -0.90
     <=",
    -0.85
    MessageTagHelper
    -0.80
     Italijanski
    -0.80
     autorytatywna
    -0.79
     ويكيپيديا
    -0.77
    Portály
    -0.77
     CreateTagHelper
    -0.77
    POSITIVE LOGITS
     fo
    0.44
     fof
    0.42
     conto
    0.40
    alanta
    0.39
     four
    0.37
     Forge
    0.36
    getReference
    0.35
     for
    0.35
     Fo
    0.35
     aten
    0.34
    Activations Density 0.002%

    No Known Activations