© 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. 20-CLT-HP
    7. 76367
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    PerformLayout
    -0.76
    tagHelperRunner
    -0.70
    帖最后由
    -0.69
    #+#
    -0.67
    بوابة
    -0.66
    AlterField
    -0.60
    DeleteBehavior
    -0.58
     jsPsych
    -0.57
     MainAxisSize
    -0.57
     createSlice
    -0.57
    POSITIVE LOGITS
     télécharge
    0.47
     sì
    0.46
     facteurs
    0.46
     gás
    0.44
    HttpClientModule
    0.43
    ICLES
    0.42
     estacionamento
    0.42
    ʤ
    0.41
    ῖς
    0.40
    RegistryLite
    0.40
    Activations Density 0.002%

    No Known Activations