© 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. 1-CLT-HP
    7. 15226
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
    Autoritní
    -0.62
    <bos>
    -0.57
     fermés
    -0.54
    XmlAccessorType
    -0.54
     automatiques
    -0.53
    godic
    -0.52
     "<?
    -0.52
     smtplib
    -0.51
     roulant
    -0.50
    Становништво
    -0.50
    POSITIVE LOGITS
    MessageTagHelper
    0.61
    writeFieldEnd
    0.55
    Clik
    0.54
    InputTagHelper
    0.46
    ISupport
    0.45
     تضيفلها
    0.44
    ToAdd
    0.44
    piro
    0.43
    Marks
    0.42
     Schülerinnen
    0.42
    Activations Density 0.018%

    No Known Activations