© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3665
    Prev
    Next
    INDEX
    Explanations

    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
     âgées
    -0.41
    FLP
    -0.40
    NewUrlParser
    -0.40
    elerik
    -0.39
    uelan
    -0.37
    UpInside
    -0.37
     théorie
    -0.37
    findpost
    -0.36
    ambiguation
    -0.35
     teoría
    -0.35
    POSITIVE LOGITS
    хьтан
    0.70
    DockStyle
    0.67
    IMPORTED
    0.66
     متعلقه
    0.66
    Geplaatst
    0.65
    Dữ
    0.64
    GEBURTSDATUM
    0.62
    tagHelperRunner
    0.61
    #+#
    0.59
    حوالہ
    0.59
    Activations Density 0.003%

    No Known Activations