© 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. 646
    Prev
    Next
    INDEX
    Explanations

    truth, verification, independence

    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
    expandindo
    -0.63
    شهاد
    -0.61
     MainAxisSize
    -0.60
    aarrggbb
    -0.56
    AndEndTag
    -0.55
    MessageTagHelper
    -0.54
     CreateTagHelper
    -0.54
     kasarigan
    -0.53
    ⓧ
    -0.51
    TypedDataSet
    -0.51
    POSITIVE LOGITS
    ="<?=
    0.51
    Forme
    0.51
    </h2>
    0.46
    Form
    0.46
    styleable
    0.45
    fromCharCode
    0.45
     formed
    0.45
    hne
    0.44
    ="<?=$
    0.44
    ########.
    0.44
    Activations Density 0.007%

    No Known Activations