© 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. 5-CLT-HP
    7. 92801
    Prev
    Next
    INDEX
    Explanations

    text snippets, context words

    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
     تضيفلها
    -0.70
    ArgsConstructor
    -0.64
     JSTOR
    -0.59
    WebServlet
    -0.57
    WebVitals
    -0.57
    GraphicsUnit
    -0.51
     Widow
    -0.51
     Era
    -0.50
    protoimpl
    -0.50
    fins
    -0.49
    POSITIVE LOGITS
    brities
    0.63
    mybatisplus
    0.54
    ItemLayout
    0.50
     EconPapers
    0.49
    ضايا
    0.48
    <bos>
    0.47
     IMDG
    0.45
    Климат
    0.44
    ోగ
    0.44
     zewnętrzne
    0.43
    Activations Density 0.000%

    No Known Activations