© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    hashing and encryption

    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
     propOrder
    -0.82
     noDo
    -0.77
    Personensuche
    -0.66
     通販
    -0.65
     незавершена
    -0.63
    abestanden
    -0.62
     betweenstory
    -0.61
    <bos>
    -0.61
    awtextra
    -0.59
    contentLoaded
    -0.59
    POSITIVE LOGITS
    v
    0.52
    5
    0.52
     vostri
    0.49
     mourut
    0.47
     mücade
    0.46
     CreateTagHelper
    0.45
    __*/
    0.45
     dovuto
    0.44
    rste
    0.43
    (),
    0.43
    Activations Density 0.007%

    No Known Activations