© 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. 97198
    Prev
    Next
    INDEX
    Explanations

    tele

    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
     purpoſe
    -0.69
     alamu
    -0.61
     Reſ
    -0.60
     diza
    -0.60
     ainfi
    -0.60
     Perſ
    -0.57
     ſta
    -0.57
     ſte
    -0.56
     auffi
    -0.56
     deſt
    -0.55
    POSITIVE LOGITS
     surla
    0.84
     <=",
    0.81
    ngdoc
    0.76
    Personensuche
    0.71
    ParallelGroup
    0.70
    RenderAtEndOf
    0.69
     NSCoder
    0.68
     pinulongan
    0.68
    PerformLayout
    0.67
    ResumeLayout
    0.66
    Activations Density 0.124%

    No Known Activations