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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94612
    Prev
    Next
    INDEX
    Explanations

    /

    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
    <bos>
    -0.68
     kasarigan
    -0.47
    ’
    -0.41
    ご了承ください
    -0.40
    IGraphics
    -0.39
    клопе
    -0.37
    ContentAsync
    -0.36
     %
    -0.35
    ільки
    -0.35
     Eleventh
    -0.35
    POSITIVE LOGITS
    webElementGuid
    0.67
    +#+
    0.64
    出版年
    0.63
    ControllerTest
    0.63
    Personendaten
    0.60
     صوتيه
    0.58
    XmlAccessType
    0.57
    TemporalType
    0.57
    SourceChecksum
    0.57
     يتيمه
    0.56
    Activations Density 0.013%

    No Known Activations