© 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. 72808
    Prev
    Next
    INDEX
    Explanations

    ora

    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
     betweenstory
    -0.80
     CreateTagHelper
    -0.79
     виправивши
    -0.76
    Hentet
    -0.69
     ComVisible
    -0.68
     مشين
    -0.65
    पया
    -0.63
    GenerationType
    -0.62
    ThemeOverlay
    -0.60
    IntoConstraints
    -0.60
    POSITIVE LOGITS
    databinding
    0.47
    skine
    0.45
     debout
    0.45
    dddd
    0.44
    desen
    0.43
     sauvages
    0.43
     compréhen
    0.42
    altung
    0.40
    DAYS
    0.40
    estimm
    0.39
    Activations Density 0.006%

    No Known Activations