© 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. 4-CLT-HP
    7. 4750
    Prev
    Next
    INDEX
    Explanations

    sandstone

    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
     betweenstory
    -0.66
    TagMode
    -0.63
     MainAxisSize
    -0.62
     المعيارى
    -0.60
    Geplaatst
    -0.59
    </tfoot>
    -0.58
    astify
    -0.57
    iastical
    -0.56
    JsonHelper
    -0.53
    StructEnd
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.70
    PreferredItem
    0.65
    NameInMap
    0.58
     corpi
    0.57
    ंदीखरीदारी
    0.54
    WriteLiteral
    0.53
     ModelExpression
    0.52
    Bodies
    0.51
    حياتها
    0.51
    isseaux
    0.50
    Activations Density 0.002%

    No Known Activations