© 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. 77344
    Prev
    Next
    INDEX
    Explanations

    .

    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
     saites
    -0.65
    XmlAccessType
    -0.60
    AndroidJUnit
    -0.58
    winder
    -0.57
     NSCoder
    -0.56
     MediatR
    -0.54
     useStyles
    -0.54
    ImageContext
    -0.53
    Xaml
    -0.53
     createState
    -0.51
    POSITIVE LOGITS
    \{\\
    0.63
     كومونز
    0.59
     transfieras
    0.57
    出版年
    0.56
     Bancroft
    0.54
    Sinopsis
    0.51
     Farmer
    0.50
    strich
    0.49
     slow
    0.49
     Literally
    0.48
    Activations Density 0.008%

    No Known Activations