© 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. 0-CLT-HP
    7. 42639
    Prev
    Next
    INDEX
    Explanations

    тся

    np_max-act · 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
     is
    -1.42
    المراجع
    -0.71
    Rohy
    -0.56
    drage
    -0.55
     είναι
    -0.52
     isn
    -0.51
     Is
    -0.51
     ist
    -0.49
     will
    -0.49
     amelyek
    -0.49
    POSITIVE LOGITS
    ViewFeatures
    0.83
     ModelRenderer
    0.75
     تضيفلها
    0.73
    IUrlHelper
    0.70
    fjspx
    0.68
    +#+#
    0.67
     protoimpl
    0.65
     onData
    0.65
    WriteTagHelper
    0.64
    .$$
    0.63
    Activations Density 0.049%

    No Known Activations