© 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. 0-CLT-HP
    7. 42895
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/specialized terms

    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
     Facebook
    -0.92
     carbon
    -0.81
    carbon
    -0.72
    SOUNDBITE
    -0.72
     Carbon
    -0.71
    Carbon
    -0.69
     Amazon
    -0.69
    Facebook
    -0.68
    fjspx
    -0.68
     Twitter
    -0.67
    POSITIVE LOGITS
     houſe
    1.33
     pleaſure
    1.30
     itſelf
    1.30
     purpoſe
    1.29
     Efq
    1.25
     Jefus
    1.23
     Majefty
    1.16
     myſelf
    1.16
     poffible
    1.13
     Monfieur
    1.12
    Activations Density 0.223%

    No Known Activations